Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4463 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.2784. Min Act: -0.1700
Data Index: 1602451 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.2784. Min Act: -0.1700
Data Index: 989093 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.1222. Min Act: -0.1700
Data Index: 4650186 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.1222. Min Act: -0.1700
Data Index: 4528863 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.0909. Min Act: -0.1700
Data Index: 1319297 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.0909. Min Act: -0.1700
Data Index: 1603391 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2784. Min Range: -6.2784
Max Act: 6.0284. Min Act: -0.1700
Data Index: 5669687 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.9659. Min Act: -0.1700
Data Index: 6203370 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.9972. Min Act: -0.1700
Data Index: 3662034 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.9347. Min Act: -0.1700
Data Index: 2374564 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.9034. Min Act: -0.1700
Data Index: 168181 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.8409. Min Act: -0.1700
Data Index: 2910180 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.8409. Min Act: -0.1700
Data Index: 1989040 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.8097. Min Act: -0.1700
Data Index: 2960089 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.8097. Min Act: -0.1700
Data Index: 2996810 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.8097. Min Act: -0.1700
Data Index: 3117438 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.8097. Min Act: -0.1700
Data Index: 1084158 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.7784. Min Act: -0.1700
Data Index: 418463 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.7472. Min Act: -0.1700
Data Index: 1860858 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2784. Min Range: -6.2784
Max Act: 5.7784. Min Act: -0.1700
Data Index: 6914960 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19