Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0174. Min Range: -7.0174
Max Act: 7.0174. Min Act: -0.1700
Data Index: 2237780 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.8612. Min Act: -0.1700
Data Index: 920903 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.8299. Min Act: -0.1700
Data Index: 43801 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6424. Min Act: -0.1700
Data Index: 1794675 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.6112. Min Act: -0.1700
Data Index: 190367 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5799. Min Act: -0.1700
Data Index: 140435 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5799. Min Act: -0.1700
Data Index: 430358 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.5487. Min Act: -0.1700
Data Index: 293345 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4862. Min Act: -0.1700
Data Index: 2758511 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4549. Min Act: -0.1700
Data Index: 7175736 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4549. Min Act: -0.1700
Data Index: 5446188 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4549. Min Act: -0.1700
Data Index: 5179355 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4237. Min Act: -0.1700
Data Index: 8768342 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4237. Min Act: -0.1700
Data Index: 6493678 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.4549. Min Act: -0.1700
Data Index: 857513 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.3612. Min Act: -0.1700
Data Index: 4136333 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.3612. Min Act: -0.1700
Data Index: 1731510 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 4551407 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 2731224 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0174. Min Range: -7.0174
Max Act: 6.3299. Min Act: -0.1700
Data Index: 5209250 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19