Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2263. Min Range: -5.2263
Max Act: 5.2263. Min Act: -0.1700
Data Index: 2405720 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.9450. Min Act: -0.1700
Data Index: 5731249 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.8200. Min Act: -0.1700
Data Index: 431079 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.8200. Min Act: -0.1700
Data Index: 516611 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.7575. Min Act: -0.1700
Data Index: 7232018 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.7575. Min Act: -0.1700
Data Index: 2322109 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.7263. Min Act: -0.1700
Data Index: 2042183 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.7263. Min Act: -0.1700
Data Index: 8819248 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6950. Min Act: -0.1700
Data Index: 7780596 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6950. Min Act: -0.1700
Data Index: 5058291 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6950. Min Act: -0.1700
Data Index: 5207081 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6950. Min Act: -0.1700
Data Index: 6849080 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6638. Min Act: -0.1700
Data Index: 4347601 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6638. Min Act: -0.1700
Data Index: 141547 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6638. Min Act: -0.1700
Data Index: 4853393 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2548859 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6325. Min Act: -0.1700
Data Index: 1540379 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6325. Min Act: -0.1700
Data Index: 3827850 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6325. Min Act: -0.1700
Data Index: 5952173 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2263. Min Range: -5.2263
Max Act: 4.6325. Min Act: -0.1700
Data Index: 5062589 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19