Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4540 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1147. Min Range: -8.1147
Max Act: 8.1147. Min Act: -0.1700
Data Index: 8551304 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1147. Min Range: -8.1147
Max Act: 8.0522. Min Act: -0.1700
Data Index: 6746529 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.8022. Min Act: -0.1700
Data Index: 285086 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.8022. Min Act: -0.1700
Data Index: 4894716 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.7710. Min Act: -0.1700
Data Index: 5104886 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.7085. Min Act: -0.1700
Data Index: 1775195 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.7085. Min Act: -0.1700
Data Index: 1189218 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.7085. Min Act: -0.1700
Data Index: 6143104 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.7085. Min Act: -0.1700
Data Index: 4456990 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.6772. Min Act: -0.1700
Data Index: 3146062 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.6147. Min Act: -0.1700
Data Index: 3190811 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.6460. Min Act: -0.1700
Data Index: 667143 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.6147. Min Act: -0.1700
Data Index: 4877846 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.5835. Min Act: -0.1700
Data Index: 937991 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.5835. Min Act: -0.1700
Data Index: 4575374 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5651191 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.5522. Min Act: -0.1700
Data Index: 6060520 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.5522. Min Act: -0.1700
Data Index: 4774767 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.4897. Min Act: -0.1700
Data Index: 8346818 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1147. Min Range: -8.1147
Max Act: 7.4897. Min Act: -0.1700
Data Index: 7661510 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19