Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2497. Min Range: -5.2497
Max Act: 5.2497. Min Act: -0.1700
Data Index: 7107532 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2497. Min Range: -5.2497
Max Act: 5.1872. Min Act: -0.1700
Data Index: 2038812 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2497. Min Range: -5.2497
Max Act: 5.0934. Min Act: -0.1700
Data Index: 6625702 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2497. Min Range: -5.2497
Max Act: 5.0309. Min Act: -0.1700
Data Index: 7496131 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2497. Min Range: -5.2497
Max Act: 5.0309. Min Act: -0.1700
Data Index: 5806782 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9997. Min Act: -0.1700
Data Index: 2089677 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9997. Min Act: -0.1700
Data Index: 5919954 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9684. Min Act: -0.1700
Data Index: 2553151 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9684. Min Act: -0.1700
Data Index: 5514190 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9997. Min Act: -0.1700
Data Index: 1355121 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9684. Min Act: -0.1700
Data Index: 4778442 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9059. Min Act: -0.1700
Data Index: 6216383 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9372. Min Act: -0.1700
Data Index: 983069 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9372. Min Act: -0.1700
Data Index: 2978335 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9059. Min Act: -0.1700
Data Index: 5143674 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9059. Min Act: -0.1700
Data Index: 5143667 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.9059. Min Act: -0.1700
Data Index: 1355111 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.8747. Min Act: -0.1700
Data Index: 6674083 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.8434. Min Act: -0.1700
Data Index: 1274853 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2497. Min Range: -5.2497
Max Act: 4.8747. Min Act: -0.1700
Data Index: 5898665 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19