Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3985 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.2815. Min Act: -0.1700
Data Index: 7754985 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.2815. Min Act: -0.1700
Data Index: 8430020 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.2501. Min Act: -0.1700
Data Index: 475478 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.1872. Min Act: -0.1700
Data Index: 8178788 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.1557. Min Act: -0.1700
Data Index: 902451 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.1242. Min Act: -0.1700
Data Index: 6271863 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.1242. Min Act: -0.1700
Data Index: 4706356 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0927. Min Act: -0.1700
Data Index: 904809 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0927. Min Act: -0.1700
Data Index: 6502381 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0612. Min Act: -0.1700
Data Index: 8387377 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0612. Min Act: -0.1700
Data Index: 291948 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0769. Min Act: -0.1700
Data Index: 1189441 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0454. Min Act: -0.1700
Data Index: 8022043 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0138. Min Act: -0.1700
Data Index: 7036144 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0296. Min Act: -0.1700
Data Index: 2943785 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0296. Min Act: -0.1700
Data Index: 1955626 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0138. Min Act: -0.1700
Data Index: 99739 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0296. Min Act: -0.1700
Data Index: 3759600 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2815. Min Range: -3.2815
Max Act: 2.9980. Min Act: -0.1700
Data Index: 2071771 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2815. Min Range: -3.2815
Max Act: 3.0138. Min Act: -0.1700
Data Index: 2363571 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19