Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6357 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0275. Min Range: -8.0275
Max Act: 8.0275. Min Act: -0.1700
Data Index: 525816 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0275. Min Range: -8.0275
Max Act: 7.4650. Min Act: -0.1700
Data Index: 8734191 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0275. Min Range: -8.0275
Max Act: 7.1837. Min Act: -0.1700
Data Index: 8477086 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0275. Min Range: -8.0275
Max Act: 7.0275. Min Act: -0.1700
Data Index: 1363081 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0275. Min Range: -8.0275
Max Act: 7.0275. Min Act: -0.1700
Data Index: 3655581 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9337. Min Act: -0.1700
Data Index: 2785423 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9650. Min Act: -0.1700
Data Index: 554074 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9650. Min Act: -0.1700
Data Index: 1790788 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9025. Min Act: -0.1700
Data Index: 6291313 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9025. Min Act: -0.1700
Data Index: 6333484 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9025. Min Act: -0.1700
Data Index: 5520702 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9025. Min Act: -0.1700
Data Index: 7430308 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9337. Min Act: -0.1700
Data Index: 2821863 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.9025. Min Act: -0.1700
Data Index: 721999 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.8712. Min Act: -0.1700
Data Index: 8734187 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.8400. Min Act: -0.1700
Data Index: 1654170 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.8087. Min Act: -0.1700
Data Index: 5660183 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.8087. Min Act: -0.1700
Data Index: 2894504 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.8400. Min Act: -0.1700
Data Index: 4676659 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0275. Min Range: -8.0275
Max Act: 6.7775. Min Act: -0.1700
Data Index: 7796074 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19