Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.2227. Min Act: -0.1700
Data Index: 5600629 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.0352. Min Act: -0.1700
Data Index: 8065600 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2227. Min Range: -6.2227
Max Act: 6.0040. Min Act: -0.1700
Data Index: 4606966 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.9727. Min Act: -0.1700
Data Index: 8065620 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1365811 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8790. Min Act: -0.1700
Data Index: 4728513 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8790. Min Act: -0.1700
Data Index: 4924407 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8477. Min Act: -0.1700
Data Index: 1697939 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8165. Min Act: -0.1700
Data Index: 2482056 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7852. Min Act: -0.1700
Data Index: 5747048 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8165. Min Act: -0.1700
Data Index: 1209743 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7852. Min Act: -0.1700
Data Index: 1065373 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7852. Min Act: -0.1700
Data Index: 6875229 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.8165. Min Act: -0.1700
Data Index: 3479263 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 3021881 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 2809466 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 4464925 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.6915. Min Act: -0.1700
Data Index: 8227427 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.7227. Min Act: -0.1700
Data Index: 4769163 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2227. Min Range: -6.2227
Max Act: 5.6915. Min Act: -0.1700
Data Index: 149158 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19