Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.5130. Min Act: -0.1700
Data Index: 3977637 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.2318. Min Act: -0.1700
Data Index: 8206701 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.2318. Min Act: -0.1700
Data Index: 1320064 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.2005. Min Act: -0.1700
Data Index: 410875 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.1693. Min Act: -0.1700
Data Index: 609492 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.1380. Min Act: -0.1700
Data Index: 673045 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.1380. Min Act: -0.1700
Data Index: 390682 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.1380. Min Act: -0.1700
Data Index: 6653118 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.1068. Min Act: -0.1700
Data Index: 3735674 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0755. Min Act: -0.1700
Data Index: 4764596 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.1068. Min Act: -0.1700
Data Index: 1037536 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0755. Min Act: -0.1700
Data Index: 222729 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 889072 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0443. Min Act: -0.1700
Data Index: 1160855 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0443. Min Act: -0.1700
Data Index: 5191879 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 1659579 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 60658 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 1822422 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 5628504 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5130. Min Range: -7.5130
Max Act: 7.0130. Min Act: -0.1700
Data Index: 2296366 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19