Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.9205. Min Act: -0.1700
Data Index: 180292 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.3892. Min Act: -0.1700
Data Index: 7237790 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.3267. Min Act: -0.1700
Data Index: 8682654 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.2955. Min Act: -0.1700
Data Index: 7731514 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.1392. Min Act: -0.1700
Data Index: 5629426 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.1705. Min Act: -0.1700
Data Index: 7411939 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0767. Min Act: -0.1700
Data Index: 3071427 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0767. Min Act: -0.1700
Data Index: 7032196 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0767. Min Act: -0.1700
Data Index: 8422489 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0455. Min Act: -0.1700
Data Index: 623333 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0142. Min Act: -0.1700
Data Index: 8636126 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0142. Min Act: -0.1700
Data Index: 2382421 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0142. Min Act: -0.1700
Data Index: 7328573 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9205. Min Range: -7.9205
Max Act: 6.9830. Min Act: -0.1700
Data Index: 7800746 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9205. Min Range: -7.9205
Max Act: 7.0142. Min Act: -0.1700
Data Index: 3153290 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9205. Min Range: -7.9205
Max Act: 6.9517. Min Act: -0.1700
Data Index: 7787074 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9205. Min Range: -7.9205
Max Act: 6.9205. Min Act: -0.1700
Data Index: 2079851 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9205. Min Range: -7.9205
Max Act: 6.9517. Min Act: -0.1700
Data Index: 7817648 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9205. Min Range: -7.9205
Max Act: 6.9205. Min Act: -0.1700
Data Index: 7163803 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9205. Min Range: -7.9205
Max Act: 6.9205. Min Act: -0.1700
Data Index: 1642936 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19