Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.9903. Min Act: -0.1700
Data Index: 1808404 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.9903. Min Act: -0.1700
Data Index: 750254 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.9590. Min Act: -0.1700
Data Index: 4693053 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.9278. Min Act: -0.1700
Data Index: 3603282 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.9278. Min Act: -0.1700
Data Index: 2633385 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.8965. Min Act: -0.1700
Data Index: 8325704 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.8965. Min Act: -0.1700
Data Index: 6021623 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.8653. Min Act: -0.1700
Data Index: 1516106 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8163352 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.8340. Min Act: -0.1700
Data Index: 1968524 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.7403. Min Act: -0.1700
Data Index: 4338220 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.7715. Min Act: -0.1700
Data Index: 7113006 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.7715. Min Act: -0.1700
Data Index: 651401 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.7403. Min Act: -0.1700
Data Index: 3759653 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.7403. Min Act: -0.1700
Data Index: 847122 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.7403. Min Act: -0.1700
Data Index: 4166522 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.6778. Min Act: -0.1700
Data Index: 7407861 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.6465. Min Act: -0.1700
Data Index: 6656681 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.6465. Min Act: -0.1700
Data Index: 3453534 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9903. Min Range: -4.9903
Max Act: 4.6465. Min Act: -0.1700
Data Index: 4419690 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19