Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 813 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2848. Min Range: -6.2848
Max Act: 6.2848. Min Act: -0.1700
Data Index: 1378834 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2848. Min Range: -6.2848
Max Act: 6.2223. Min Act: -0.1700
Data Index: 840980 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2848. Min Range: -6.2848
Max Act: 6.1598. Min Act: -0.1700
Data Index: 4750611 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2848. Min Range: -6.2848
Max Act: 6.0661. Min Act: -0.1700
Data Index: 2631409 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2848. Min Range: -6.2848
Max Act: 6.0036. Min Act: -0.1700
Data Index: 5497486 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.9723. Min Act: -0.1700
Data Index: 1003755 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.9098. Min Act: -0.1700
Data Index: 6270023 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.9723. Min Act: -0.1700
Data Index: 4504495 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.9098. Min Act: -0.1700
Data Index: 326980 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.8786. Min Act: -0.1700
Data Index: 7444151 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.8473. Min Act: -0.1700
Data Index: 1838538 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.7848. Min Act: -0.1700
Data Index: 8752195 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.8161. Min Act: -0.1700
Data Index: 7414132 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.7848. Min Act: -0.1700
Data Index: 6315189 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.7223. Min Act: -0.1700
Data Index: 740224 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.7848. Min Act: -0.1700
Data Index: 685180 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.7536. Min Act: -0.1700
Data Index: 8285429 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.7223. Min Act: -0.1700
Data Index: 3989609 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.6911. Min Act: -0.1700
Data Index: 4801842 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2848. Min Range: -6.2848
Max Act: 5.6598. Min Act: -0.1700
Data Index: 7976429 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19