Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3336. Min Range: -7.3336
Max Act: 7.3336. Min Act: -0.1700
Data Index: 4395926 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3336. Min Range: -7.3336
Max Act: 7.2086. Min Act: -0.1700
Data Index: 4715325 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3336. Min Range: -7.3336
Max Act: 7.1461. Min Act: -0.1700
Data Index: 7682947 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.9898. Min Act: -0.1700
Data Index: 266937 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.9898. Min Act: -0.1700
Data Index: 959836 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.9273. Min Act: -0.1700
Data Index: 8515375 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.9273. Min Act: -0.1700
Data Index: 6155661 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8961. Min Act: -0.1700
Data Index: 6251384 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8961. Min Act: -0.1700
Data Index: 5516609 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8648. Min Act: -0.1700
Data Index: 7937643 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8648. Min Act: -0.1700
Data Index: 1573593 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8648. Min Act: -0.1700
Data Index: 2398570 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8648. Min Act: -0.1700
Data Index: 1597919 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8336. Min Act: -0.1700
Data Index: 8462128 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8023. Min Act: -0.1700
Data Index: 1685945 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8023. Min Act: -0.1700
Data Index: 2869385 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8336. Min Act: -0.1700
Data Index: 5691725 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8336. Min Act: -0.1700
Data Index: 7339534 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8023. Min Act: -0.1700
Data Index: 6523629 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3336. Min Range: -7.3336
Max Act: 6.8336. Min Act: -0.1700
Data Index: 3057880 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19