Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1418. Min Range: -9.1418
Max Act: 9.1418. Min Act: -0.1700
Data Index: 8723459 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1418. Min Range: -9.1418
Max Act: 9.0168. Min Act: -0.1700
Data Index: 2557521 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1418. Min Range: -9.1418
Max Act: 9.0168. Min Act: -0.1700
Data Index: 700039 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.8918. Min Act: -0.1700
Data Index: 2712818 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.8293. Min Act: -0.1700
Data Index: 4039676 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.8293. Min Act: -0.1700
Data Index: 4062573 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7668. Min Act: -0.1700
Data Index: 4052062 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7668. Min Act: -0.1700
Data Index: 1653429 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7668. Min Act: -0.1700
Data Index: 8629939 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7668. Min Act: -0.1700
Data Index: 7418298 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7043. Min Act: -0.1700
Data Index: 536654 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7043. Min Act: -0.1700
Data Index: 1064204 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7043. Min Act: -0.1700
Data Index: 211531 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.7043. Min Act: -0.1700
Data Index: 2588716 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.6418. Min Act: -0.1700
Data Index: 664755 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.6418. Min Act: -0.1700
Data Index: 946309 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.5793. Min Act: -0.1700
Data Index: 4902145 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.5168. Min Act: -0.1700
Data Index: 5082320 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.5168. Min Act: -0.1700
Data Index: 3973176 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1418. Min Range: -9.1418
Max Act: 8.5168. Min Act: -0.1699
Data Index: 4089336 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19