Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0034. Min Range: -5.0034
Max Act: 5.0034. Min Act: -0.1700
Data Index: 3144417 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.9409. Min Act: -0.1700
Data Index: 7371214 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.9096. Min Act: -0.1700
Data Index: 4981080 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.9096. Min Act: -0.1700
Data Index: 1534096 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.9096. Min Act: -0.1700
Data Index: 1090582 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8784. Min Act: -0.1700
Data Index: 7613006 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8784. Min Act: -0.1700
Data Index: 8265404 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8784. Min Act: -0.1700
Data Index: 7735125 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8159. Min Act: -0.1700
Data Index: 7427087 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8159. Min Act: -0.1700
Data Index: 853390 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8471. Min Act: -0.1700
Data Index: 4085840 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8159. Min Act: -0.1700
Data Index: 7427085 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8159. Min Act: -0.1700
Data Index: 1375058 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8159. Min Act: -0.1700
Data Index: 1545317 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7846. Min Act: -0.1700
Data Index: 8464701 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7221. Min Act: -0.1700
Data Index: 577903 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7221. Min Act: -0.1700
Data Index: 7873398 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7221. Min Act: -0.1700
Data Index: 4764202 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7221. Min Act: -0.1700
Data Index: 3648722 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6909. Min Act: -0.1700
Data Index: 4113391 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19