Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1854 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2443. Min Range: -7.2443
Max Act: 7.2443. Min Act: -0.1700
Data Index: 656297 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.9943. Min Act: -0.1698
Data Index: 5442735 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.9005. Min Act: -0.1692
Data Index: 1557610 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.9005. Min Act: -0.1697
Data Index: 8161331 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.8068. Min Act: -0.1700
Data Index: 3938204 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.8068. Min Act: -0.1700
Data Index: 7239753 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.7755. Min Act: -0.1700
Data Index: 3408089 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.7755. Min Act: -0.1698
Data Index: 4827084 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.7443. Min Act: -0.1700
Data Index: 3718728 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6505. Min Act: -0.1658
Data Index: 5396930 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6505. Min Act: -0.1699
Data Index: 1729810 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6505. Min Act: -0.1600
Data Index: 3349562 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6505. Min Act: -0.1699
Data Index: 8597156 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6505. Min Act: -0.1700
Data Index: 4706085 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6193. Min Act: -0.1700
Data Index: 374160 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6193. Min Act: -0.1694
Data Index: 724717 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6193. Min Act: -0.1700
Data Index: 4038082 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6193. Min Act: -0.1501
Data Index: 4188994 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6193. Min Act: -0.1700
Data Index: 5783699 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2443. Min Range: -7.2443
Max Act: 6.6193. Min Act: -0.1698
Data Index: 1151956 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19