Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.6502. Min Act: -0.1700
Data Index: 5637118 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.6189. Min Act: -0.1700
Data Index: 4107913 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5876. Min Act: -0.1700
Data Index: 6979026 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5876. Min Act: -0.1700
Data Index: 1247949 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5563. Min Act: -0.1700
Data Index: 7377270 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5563. Min Act: -0.1700
Data Index: 567857 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5876. Min Act: -0.1700
Data Index: 7646729 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5563. Min Act: -0.1700
Data Index: 4678745 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5563. Min Act: -0.1700
Data Index: 4146778 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5563. Min Act: -0.1700
Data Index: 8718742 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5249. Min Act: -0.1700
Data Index: 1542443 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4936. Min Act: -0.1700
Data Index: 5126018 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.5249. Min Act: -0.1700
Data Index: 5694797 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4780. Min Act: -0.1700
Data Index: 2058481 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4936. Min Act: -0.1700
Data Index: 8477882 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4780. Min Act: -0.1700
Data Index: 3669100 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4780. Min Act: -0.1700
Data Index: 6684526 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4936. Min Act: -0.1700
Data Index: 4501677 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4780. Min Act: -0.1700
Data Index: 2373651 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6502. Min Range: -3.6502
Max Act: 3.4780. Min Act: -0.1700
Data Index: 2488467 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19