Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.5104. Min Act: -0.1700
Data Index: 8049900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3854. Min Act: -0.1700
Data Index: 865218 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3854. Min Act: -0.1700
Data Index: 8468948 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3854. Min Act: -0.1700
Data Index: 3365057 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 5944616 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3541. Min Act: -0.1700
Data Index: 5132515 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 7739392 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3541. Min Act: -0.1700
Data Index: 3415123 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2916. Min Act: -0.1700
Data Index: 3081427 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 1179528 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 5019890 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 701995 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2916. Min Act: -0.1700
Data Index: 4401377 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 378194 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2604. Min Act: -0.1700
Data Index: 2801714 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2916. Min Act: -0.1700
Data Index: 224969 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 4697801 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2916. Min Act: -0.1700
Data Index: 8058083 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2916. Min Act: -0.1700
Data Index: 4526411 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2604. Min Act: -0.1700
Data Index: 6135125 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19