Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.9181. Min Act: -0.1700
Data Index: 1740663 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.8546. Min Act: -0.1700
Data Index: 3887599 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.8069. Min Act: -0.1700
Data Index: 8239615 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7751. Min Act: -0.1700
Data Index: 4666098 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7591. Min Act: -0.1700
Data Index: 8191617 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7432. Min Act: -0.1700
Data Index: 1931576 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7432. Min Act: -0.1700
Data Index: 5310962 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7272. Min Act: -0.1700
Data Index: 1242728 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7112. Min Act: -0.1700
Data Index: 8186719 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.7112. Min Act: -0.1700
Data Index: 2956397 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6952. Min Act: -0.1700
Data Index: 4807043 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6952. Min Act: -0.1700
Data Index: 2436407 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6792. Min Act: -0.1700
Data Index: 6036652 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6632. Min Act: -0.1700
Data Index: 5739017 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6632. Min Act: -0.1700
Data Index: 5876868 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6792. Min Act: -0.1700
Data Index: 1986111 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6471. Min Act: -0.1700
Data Index: 3960216 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6632. Min Act: -0.1700
Data Index: 4366549 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6471. Min Act: -0.1700
Data Index: 8026534 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9181. Min Range: -2.9181
Max Act: 2.6471. Min Act: -0.1700
Data Index: 4427522 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19