Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.7052. Min Act: -0.1700
Data Index: 1099454 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.7052. Min Act: -0.1700
Data Index: 683449 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.5802. Min Act: -0.1700
Data Index: 189646 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.4552. Min Act: -0.1700
Data Index: 1807060 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.4239. Min Act: -0.1700
Data Index: 7047052 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.4239. Min Act: -0.1700
Data Index: 7746083 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.4239. Min Act: -0.1700
Data Index: 2442671 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.3927. Min Act: -0.1700
Data Index: 5697341 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.4239. Min Act: -0.1700
Data Index: 5356575 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.3614. Min Act: -0.1700
Data Index: 665568 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.3302. Min Act: -0.1700
Data Index: 4726267 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2989. Min Act: -0.1700
Data Index: 7611839 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.3302. Min Act: -0.1700
Data Index: 6767443 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2677. Min Act: -0.1700
Data Index: 1412113 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2677. Min Act: -0.1700
Data Index: 4745333 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2364. Min Act: -0.1700
Data Index: 2423540 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2677. Min Act: -0.1700
Data Index: 633320 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2052. Min Act: -0.1700
Data Index: 6805411 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.2052. Min Act: -0.1700
Data Index: 2212401 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7052. Min Range: -6.7052
Max Act: 6.1739. Min Act: -0.1700
Data Index: 1838586 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19