Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.3572. Min Act: -0.1700
Data Index: 2738898 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.2947. Min Act: -0.1700
Data Index: 6355770 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.1384. Min Act: -0.1700
Data Index: 5389390 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.1384. Min Act: -0.1700
Data Index: 5443899 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.1384. Min Act: -0.1700
Data Index: 661551 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0759. Min Act: -0.1700
Data Index: 3815525 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0759. Min Act: -0.1700
Data Index: 2532084 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0759. Min Act: -0.1700
Data Index: 1247578 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0447. Min Act: -0.1700
Data Index: 8821078 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0447. Min Act: -0.1700
Data Index: 4732138 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0447. Min Act: -0.1700
Data Index: 1992536 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0134. Min Act: -0.1700
Data Index: 8287077 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0134. Min Act: -0.1700
Data Index: 3555876 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0134. Min Act: -0.1700
Data Index: 8433907 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0134. Min Act: -0.1700
Data Index: 8010831 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3572. Min Range: -4.3572
Max Act: 4.0134. Min Act: -0.1700
Data Index: 7966039 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3572. Min Range: -4.3572
Max Act: 3.9822. Min Act: -0.1700
Data Index: 5179826 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3572. Min Range: -4.3572
Max Act: 3.9822. Min Act: -0.1700
Data Index: 3909619 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3572. Min Range: -4.3572
Max Act: 3.9822. Min Act: -0.1700
Data Index: 6983726 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3572. Min Range: -4.3572
Max Act: 3.9509. Min Act: -0.1700
Data Index: 6504 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19