Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2619 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.5540. Min Act: -0.1700
Data Index: 4098432 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.4290. Min Act: -0.1700
Data Index: 3904303 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.4290. Min Act: -0.1700
Data Index: 2383131 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.4290. Min Act: -0.1700
Data Index: 1611750 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3665. Min Act: -0.1700
Data Index: 591940 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3665. Min Act: -0.1700
Data Index: 7938547 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 2886029 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 5456551 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 6120502 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 6869613 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 5829346 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 6885785 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3040. Min Act: -0.1700
Data Index: 7471207 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3353. Min Act: -0.1700
Data Index: 2329819 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3040. Min Act: -0.1700
Data Index: 617897 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.2728. Min Act: -0.1700
Data Index: 1058601 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.3040. Min Act: -0.1700
Data Index: 3953036 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.2415. Min Act: -0.1700
Data Index: 5599138 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.2728. Min Act: -0.1700
Data Index: 5013290 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5540. Min Range: -5.5540
Max Act: 5.2415. Min Act: -0.1700
Data Index: 3478834 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19