Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1339 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.8334. Min Act: -0.1700
Data Index: 8580995 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.7084. Min Act: -0.1700
Data Index: 3827991 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 4807260 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.4584. Min Act: -0.1700
Data Index: 2400882 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 4613171 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.4584. Min Act: -0.1700
Data Index: 4399989 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 7128354 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 8632606 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 7976840 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 765749 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3334. Min Act: -0.1700
Data Index: 5489907 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3334. Min Act: -0.1700
Data Index: 6290610 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2709. Min Act: -0.1700
Data Index: 597434 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3334. Min Act: -0.1700
Data Index: 6269705 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2709. Min Act: -0.1700
Data Index: 6598942 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2709. Min Act: -0.1700
Data Index: 738362 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3334. Min Act: -0.1700
Data Index: 8785914 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2709. Min Act: -0.1700
Data Index: 1765629 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2397. Min Act: -0.1700
Data Index: 1750598 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2084. Min Act: -0.1700
Data Index: 7504538 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19