Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 450 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.7116. Min Act: -0.1700
Data Index: 3825573 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.6178. Min Act: -0.1700
Data Index: 7345410 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1130698 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 6746641 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4928. Min Act: -0.1700
Data Index: 8364875 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4928. Min Act: -0.1700
Data Index: 6827883 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4928. Min Act: -0.1700
Data Index: 4594905 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4928. Min Act: -0.1700
Data Index: 4569474 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4616. Min Act: -0.1700
Data Index: 1959163 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4616. Min Act: -0.1700
Data Index: 7552134 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 1434866 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 5891187 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 4481502 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 4466633 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 3645773 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 6827882 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.3991. Min Act: -0.1700
Data Index: 6878752 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 2950021 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 2631316 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4303. Min Act: -0.1700
Data Index: 2701056 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19