Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.4802. Min Act: -0.1700
Data Index: 2923325 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.4177. Min Act: -0.1700
Data Index: 214637 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.2615. Min Act: -0.1700
Data Index: 8144217 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.1990. Min Act: -0.1700
Data Index: 7344502 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.1677. Min Act: -0.1700
Data Index: 6867693 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.1677. Min Act: -0.1700
Data Index: 789107 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.1677. Min Act: -0.1700
Data Index: 1321722 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.1365. Min Act: -0.1700
Data Index: 6028602 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0740. Min Act: -0.1700
Data Index: 7209801 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.1052. Min Act: -0.1700
Data Index: 3400849 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0740. Min Act: -0.1700
Data Index: 2034742 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0427. Min Act: -0.1700
Data Index: 2357244 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0427. Min Act: -0.1700
Data Index: 4730305 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0427. Min Act: -0.1700
Data Index: 3305133 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0115. Min Act: -0.1700
Data Index: 5872321 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0427. Min Act: -0.1700
Data Index: 4312540 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0115. Min Act: -0.1700
Data Index: 4020680 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0115. Min Act: -0.1700
Data Index: 5778716 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0427. Min Act: -0.1700
Data Index: 6970962 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4802. Min Range: -6.4802
Max Act: 6.0427. Min Act: -0.1700
Data Index: 6801440 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19