Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.5251. Min Act: -0.1700
Data Index: 2468013 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.4311. Min Act: -0.1700
Data Index: 7278065 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.4311. Min Act: -0.1700
Data Index: 1851102 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.4311. Min Act: -0.1700
Data Index: 3310682 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.4311. Min Act: -0.1700
Data Index: 3179932 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3998. Min Act: -0.1700
Data Index: 4116497 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3998. Min Act: -0.1700
Data Index: 2437606 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 6359501 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 4582664 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 3179931 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 1570306 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 4322933 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 8555928 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3684. Min Act: -0.1700
Data Index: 6500389 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3371. Min Act: -0.1700
Data Index: 1570309 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3371. Min Act: -0.1700
Data Index: 2211674 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3371. Min Act: -0.1700
Data Index: 1570323 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3371. Min Act: -0.1700
Data Index: 1570292 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3057. Min Act: -0.1700
Data Index: 1570287 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5251. Min Range: -3.5251
Max Act: 3.3371. Min Act: -0.1700
Data Index: 4909293 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19