Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.8118. Min Act: -0.1700
Data Index: 2875394 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.7805. Min Act: -0.1700
Data Index: 1768058 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.7493. Min Act: -0.1700
Data Index: 391906 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4239937 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2382649 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.7493. Min Act: -0.1700
Data Index: 4746791 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.6868. Min Act: -0.1700
Data Index: 6754127 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.6868. Min Act: -0.1700
Data Index: 7326447 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.6555. Min Act: -0.1700
Data Index: 4985606 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5930. Min Act: -0.1700
Data Index: 4809622 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5930. Min Act: -0.1700
Data Index: 5092503 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5618. Min Act: -0.1700
Data Index: 1065307 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5618. Min Act: -0.1700
Data Index: 4767849 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5618. Min Act: -0.1700
Data Index: 8739441 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5305. Min Act: -0.1700
Data Index: 5558741 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.5618. Min Act: -0.1700
Data Index: 5975440 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.4993. Min Act: -0.1700
Data Index: 199641 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.4680. Min Act: -0.1700
Data Index: 2014426 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.4680. Min Act: -0.1700
Data Index: 2019689 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8118. Min Range: -5.8118
Max Act: 5.4680. Min Act: -0.1700
Data Index: 5195995 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19