Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.0655. Min Range: -11.0655
Max Act: 11.0655. Min Act: -0.1700
Data Index: 7356659 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.6905. Min Act: -0.1700
Data Index: 7610890 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.5655. Min Act: -0.1700
Data Index: 2546336 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.4405. Min Act: -0.1700
Data Index: 8795757 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3780. Min Act: -0.1700
Data Index: 1113160 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.4405. Min Act: -0.1700
Data Index: 7827143 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3780. Min Act: -0.1700
Data Index: 2606521 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3780. Min Act: -0.1700
Data Index: 472062 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.4405. Min Act: -0.1700
Data Index: 6200944 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3780. Min Act: -0.1700
Data Index: 6367905 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3155. Min Act: -0.1700
Data Index: 3924549 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3155. Min Act: -0.1700
Data Index: 2103667 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3155. Min Act: -0.1700
Data Index: 2822348 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3155. Min Act: -0.1700
Data Index: 3121738 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.2530. Min Act: -0.1700
Data Index: 2906273 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.1905. Min Act: -0.1700
Data Index: 7850484 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.2530. Min Act: -0.1700
Data Index: 6143801 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.2530. Min Act: -0.1700
Data Index: 3453384 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.3155. Min Act: -0.1700
Data Index: 8450464 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0655. Min Range: -11.0655
Max Act: 10.1905. Min Act: -0.1700
Data Index: 3305197 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19