Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.7307. Min Act: -0.1700
Data Index: 915439 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.6369. Min Act: -0.1700
Data Index: 3726341 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.5432. Min Act: -0.1700
Data Index: 869787 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.4807. Min Act: -0.1700
Data Index: 7406514 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.4807. Min Act: -0.1700
Data Index: 8782835 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.4494. Min Act: -0.1700
Data Index: 7191119 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.4182. Min Act: -0.1700
Data Index: 120444 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3869. Min Act: -0.1700
Data Index: 2627152 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.4182. Min Act: -0.1700
Data Index: 3040748 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3869. Min Act: -0.1700
Data Index: 2553047 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3869. Min Act: -0.1700
Data Index: 1426623 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3557. Min Act: -0.1700
Data Index: 854905 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3244. Min Act: -0.1700
Data Index: 6088744 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3557. Min Act: -0.1700
Data Index: 4461360 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3557. Min Act: -0.1700
Data Index: 932264 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3557. Min Act: -0.1700
Data Index: 1593635 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3244. Min Act: -0.1700
Data Index: 5171577 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3244. Min Act: -0.1700
Data Index: 6467171 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3244. Min Act: -0.1700
Data Index: 6529368 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7307. Min Range: -4.7307
Max Act: 4.3244. Min Act: -0.1700
Data Index: 2027007 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19