Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4549 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.7334. Min Act: -0.1700
Data Index: 7512263 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.7334. Min Act: -0.1700
Data Index: 3361065 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.4834. Min Act: -0.1700
Data Index: 1370406 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.4209. Min Act: -0.1700
Data Index: 1769209 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.4209. Min Act: -0.1700
Data Index: 6433547 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.3584. Min Act: -0.1700
Data Index: 4720524 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.3584. Min Act: -0.1700
Data Index: 230348 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2959. Min Act: -0.1700
Data Index: 817968 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2959. Min Act: -0.1700
Data Index: 6981659 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2959. Min Act: -0.1700
Data Index: 5395922 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 4910 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 1874748 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 7476767 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 3630441 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 8562335 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 770075 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.2334. Min Act: -0.1700
Data Index: 943117 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.1709. Min Act: -0.1700
Data Index: 8132421 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.1709. Min Act: -0.1700
Data Index: 2934687 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7334. Min Range: -9.7334
Max Act: 9.1709. Min Act: -0.1700
Data Index: 5175008 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19