Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.7582. Min Act: -0.1700
Data Index: 4785371 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.6332. Min Act: -0.1700
Data Index: 381289 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.5395. Min Act: -0.1700
Data Index: 7633854 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.5395. Min Act: -0.1700
Data Index: 7868371 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4770. Min Act: -0.1700
Data Index: 989593 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4770. Min Act: -0.1700
Data Index: 7082543 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4770. Min Act: -0.1700
Data Index: 5458534 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.5082. Min Act: -0.1700
Data Index: 5195442 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4457. Min Act: -0.1700
Data Index: 1607199 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4770. Min Act: -0.1700
Data Index: 2506890 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4145. Min Act: -0.1700
Data Index: 1327115 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4457. Min Act: -0.1700
Data Index: 6759832 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4145. Min Act: -0.1700
Data Index: 2612019 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4457. Min Act: -0.1700
Data Index: 4919471 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4145. Min Act: -0.1700
Data Index: 4876256 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.4145. Min Act: -0.1700
Data Index: 8045787 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.3832. Min Act: -0.1700
Data Index: 1163594 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.3832. Min Act: -0.1700
Data Index: 4973723 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.3832. Min Act: -0.1700
Data Index: 771432 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7582. Min Range: -4.7582
Max Act: 4.3832. Min Act: -0.1700
Data Index: 1916723 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19