Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.7790. Min Act: -0.1700
Data Index: 881560 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.6540. Min Act: -0.1700
Data Index: 8110749 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.6540. Min Act: -0.1700
Data Index: 8789265 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.5602. Min Act: -0.1700
Data Index: 5878035 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.5602. Min Act: -0.1700
Data Index: 975486 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.5290. Min Act: -0.1700
Data Index: 4585328 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.4665. Min Act: -0.1700
Data Index: 6601310 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.4665. Min Act: -0.1700
Data Index: 2129103 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.4352. Min Act: -0.1700
Data Index: 328713 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.3727. Min Act: -0.1700
Data Index: 3386266 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.3415. Min Act: -0.1700
Data Index: 8222334 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.3415. Min Act: -0.1700
Data Index: 8762366 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.3102. Min Act: -0.1700
Data Index: 8535995 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.3102. Min Act: -0.1700
Data Index: 8640344 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.2790. Min Act: -0.1700
Data Index: 1568286 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.2477. Min Act: -0.1700
Data Index: 5695634 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.2477. Min Act: -0.1700
Data Index: 8215108 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.2477. Min Act: -0.1700
Data Index: 1731255 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.2165. Min Act: -0.1700
Data Index: 6807310 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7790. Min Range: -6.7790
Max Act: 6.2165. Min Act: -0.1700
Data Index: 6735001 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19