Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.5324. Min Act: -0.1700
Data Index: 7317423 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.4699. Min Act: -0.1700
Data Index: 1601117 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.3761. Min Act: -0.1700
Data Index: 3313868 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.3761. Min Act: -0.1700
Data Index: 3019514 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.3449. Min Act: -0.1700
Data Index: 7135198 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2824. Min Act: -0.1700
Data Index: 5073698 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2824. Min Act: -0.1700
Data Index: 1835414 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2511. Min Act: -0.1700
Data Index: 6608540 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2511. Min Act: -0.1700
Data Index: 7644525 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2511. Min Act: -0.1700
Data Index: 6264057 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2511. Min Act: -0.1700
Data Index: 3814786 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2511. Min Act: -0.1700
Data Index: 384445 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2199. Min Act: -0.1700
Data Index: 6821253 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2199. Min Act: -0.1700
Data Index: 3146575 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2199. Min Act: -0.1700
Data Index: 3957618 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.1886. Min Act: -0.1700
Data Index: 1004065 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.2199. Min Act: -0.1700
Data Index: 1269959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2249241 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.1886. Min Act: -0.1700
Data Index: 4058302 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5324. Min Range: -5.5324
Max Act: 5.1886. Min Act: -0.1700
Data Index: 2219074 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19