Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.6640. Min Act: -0.1700
Data Index: 6963265 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.4765. Min Act: -0.1700
Data Index: 7049886 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.2890. Min Act: -0.1700
Data Index: 7556547 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.2890. Min Act: -0.1700
Data Index: 5738308 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.2265. Min Act: -0.1700
Data Index: 6499807 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1640. Min Act: -0.1700
Data Index: 1655930 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1953. Min Act: -0.1700
Data Index: 2333638 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.2265. Min Act: -0.1700
Data Index: 1651510 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1640. Min Act: -0.1700
Data Index: 668780 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1640. Min Act: -0.1700
Data Index: 8656236 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1328. Min Act: -0.1700
Data Index: 2218689 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1640. Min Act: -0.1700
Data Index: 7772770 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.1015. Min Act: -0.1700
Data Index: 3104826 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0703. Min Act: -0.1700
Data Index: 8342252 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0703. Min Act: -0.1700
Data Index: 1674270 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0390. Min Act: -0.1700
Data Index: 5001376 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0078. Min Act: -0.1700
Data Index: 2833107 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0078. Min Act: -0.1700
Data Index: 4886370 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0390. Min Act: -0.1700
Data Index: 8389392 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6640. Min Range: -6.6640
Max Act: 6.0078. Min Act: -0.1700
Data Index: 2996770 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19