Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 295 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.9034. Min Act: -0.1700
Data Index: 3246941 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.9034. Min Act: -0.1700
Data Index: 4808584 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.8409. Min Act: -0.1700
Data Index: 1136661 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.6847. Min Act: -0.1700
Data Index: 2397655 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.5284. Min Act: -0.1700
Data Index: 2876756 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.5284. Min Act: -0.1700
Data Index: 513518 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.5284. Min Act: -0.1700
Data Index: 1460479 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.4659. Min Act: -0.1700
Data Index: 3651672 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.4347. Min Act: -0.1700
Data Index: 3415138 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.4347. Min Act: -0.1700
Data Index: 392552 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3722. Min Act: -0.1700
Data Index: 1551153 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.4034. Min Act: -0.1700
Data Index: 79373 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3722. Min Act: -0.1700
Data Index: 306370 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3409. Min Act: -0.1700
Data Index: 7753734 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3409. Min Act: -0.1700
Data Index: 8422972 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3722. Min Act: -0.1700
Data Index: 6090048 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3722. Min Act: -0.1700
Data Index: 7352622 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3097. Min Act: -0.1700
Data Index: 1491774 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3409. Min Act: -0.1700
Data Index: 2398614 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9034. Min Range: -6.9034
Max Act: 6.3097. Min Act: -0.1700
Data Index: 2630338 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19