Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.7518. Min Act: -0.1700
Data Index: 6166269 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.5330. Min Act: -0.1700
Data Index: 2595648 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.4705. Min Act: -0.1700
Data Index: 705106 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.4393. Min Act: -0.1700
Data Index: 8410635 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.4080. Min Act: -0.1700
Data Index: 7535449 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3143. Min Act: -0.1700
Data Index: 6745090 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3768. Min Act: -0.1700
Data Index: 7160704 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3455. Min Act: -0.1700
Data Index: 4521195 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3455. Min Act: -0.1700
Data Index: 4817374 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3143. Min Act: -0.1700
Data Index: 2731815 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3455. Min Act: -0.1700
Data Index: 1274475 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3143. Min Act: -0.1700
Data Index: 7927649 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2830. Min Act: -0.1700
Data Index: 1233101 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2830. Min Act: -0.1700
Data Index: 7631987 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2518. Min Act: -0.1700
Data Index: 3394173 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.3143. Min Act: -0.1700
Data Index: 561116 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2830. Min Act: -0.1700
Data Index: 97503 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2830. Min Act: -0.1700
Data Index: 3760854 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2518. Min Act: -0.1700
Data Index: 4817375 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7518. Min Range: -6.7518
Max Act: 6.2518. Min Act: -0.1700
Data Index: 7535450 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19