Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.6881. Min Act: -0.1700
Data Index: 5663280 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.6881. Min Act: -0.1700
Data Index: 690836 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.6256. Min Act: -0.1700
Data Index: 90533 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.5944. Min Act: -0.1700
Data Index: 8021623 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.5944. Min Act: -0.1700
Data Index: 4685694 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.5631. Min Act: -0.1700
Data Index: 3040576 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.5319. Min Act: -0.1700
Data Index: 4841035 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.5006. Min Act: -0.1700
Data Index: 1047851 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.4694. Min Act: -0.1700
Data Index: 2096506 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.4694. Min Act: -0.1700
Data Index: 283822 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.4381. Min Act: -0.1700
Data Index: 4776662 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.4381. Min Act: -0.1700
Data Index: 7809593 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.4069. Min Act: -0.1700
Data Index: 8824100 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.3756. Min Act: -0.1700
Data Index: 4776924 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.3444. Min Act: -0.1700
Data Index: 8734665 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.4069. Min Act: -0.1700
Data Index: 984053 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.3444. Min Act: -0.1700
Data Index: 85749 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.3444. Min Act: -0.1700
Data Index: 4298165 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.3444. Min Act: -0.1700
Data Index: 2031543 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6881. Min Range: -4.6881
Max Act: 4.3444. Min Act: -0.1700
Data Index: 5030717 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19