Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.6108. Min Act: -0.1700
Data Index: 8218075 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.5483. Min Act: -0.1700
Data Index: 2145761 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.4858. Min Act: -0.1700
Data Index: 2737294 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.4858. Min Act: -0.1700
Data Index: 648963 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.4858. Min Act: -0.1700
Data Index: 7225138 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.4233. Min Act: -0.1700
Data Index: 7225136 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.4858. Min Act: -0.1700
Data Index: 3592286 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.4233. Min Act: -0.1700
Data Index: 8701900 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.3608. Min Act: -0.1700
Data Index: 5812119 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.3608. Min Act: -0.1700
Data Index: 4414855 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.3608. Min Act: -0.1700
Data Index: 7612252 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.3608. Min Act: -0.1700
Data Index: 5568418 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.3608. Min Act: -0.1700
Data Index: 2901857 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2983. Min Act: -0.1700
Data Index: 6827352 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2358. Min Act: -0.1700
Data Index: 5326869 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2358. Min Act: -0.1700
Data Index: 1280680 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2358. Min Act: -0.1700
Data Index: 5370837 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2358. Min Act: -0.1700
Data Index: 8585125 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2358. Min Act: -0.1700
Data Index: 8654283 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6108. Min Range: -8.6108
Max Act: 8.2983. Min Act: -0.1700
Data Index: 6265175 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19