Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4947 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.6583. Min Act: -0.1700
Data Index: 7901232 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.6114. Min Act: -0.1700
Data Index: 5785075 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5644. Min Act: -0.1700
Data Index: 4577557 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5801. Min Act: -0.1700
Data Index: 1127996 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5644. Min Act: -0.1700
Data Index: 4861553 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5644. Min Act: -0.1700
Data Index: 8681510 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5331. Min Act: -0.1700
Data Index: 4806458 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4705. Min Act: -0.1700
Data Index: 4756225 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4548. Min Act: -0.1700
Data Index: 8675619 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4861. Min Act: -0.1700
Data Index: 4225909 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4391. Min Act: -0.1700
Data Index: 842774 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4705. Min Act: -0.1700
Data Index: 5483073 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4548. Min Act: -0.1700
Data Index: 7181719 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4391. Min Act: -0.1700
Data Index: 2026384 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4548. Min Act: -0.1700
Data Index: 2414457 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4391. Min Act: -0.1700
Data Index: 5249403 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4391. Min Act: -0.1700
Data Index: 1910316 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4234. Min Act: -0.1700
Data Index: 4744930 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4234. Min Act: -0.1700
Data Index: 1195509 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.3921. Min Act: -0.1700
Data Index: 6660515 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19