Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3739 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1858. Min Range: -8.1858
Max Act: 8.1858. Min Act: -0.1700
Data Index: 4295081 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1858. Min Range: -8.1858
Max Act: 8.1858. Min Act: -0.1700
Data Index: 2884566 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1858. Min Range: -8.1858
Max Act: 8.1233. Min Act: -0.1700
Data Index: 7149683 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1858. Min Range: -8.1858
Max Act: 8.1233. Min Act: -0.1700
Data Index: 5866664 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1858. Min Range: -8.1858
Max Act: 8.0608. Min Act: -0.1700
Data Index: 2690530 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.9358. Min Act: -0.1700
Data Index: 2751936 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1858. Min Range: -8.1858
Max Act: 8.0608. Min Act: -0.1700
Data Index: 3098670 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8733. Min Act: -0.1700
Data Index: 4013883 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8733. Min Act: -0.1700
Data Index: 2991565 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8733. Min Act: -0.1700
Data Index: 6479801 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8108. Min Act: -0.1700
Data Index: 4924739 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8108. Min Act: -0.1700
Data Index: 57985 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8108. Min Act: -0.1700
Data Index: 5191147 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.8108. Min Act: -0.1700
Data Index: 7700219 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.7483. Min Act: -0.1700
Data Index: 4829705 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.6858. Min Act: -0.1700
Data Index: 114351 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.7483. Min Act: -0.1700
Data Index: 1277301 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.7483. Min Act: -0.1700
Data Index: 6147512 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.7483. Min Act: -0.1700
Data Index: 1750087 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1858. Min Range: -8.1858
Max Act: 7.6545. Min Act: -0.1700
Data Index: 8509440 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19