Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.9296. Min Act: -0.1700
Data Index: 3950450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.9296. Min Act: -0.1700
Data Index: 3553344 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.9296. Min Act: -0.1700
Data Index: 2752180 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8983. Min Act: -0.1700
Data Index: 2742402 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 935986 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8358. Min Act: -0.1699
Data Index: 3843511 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 3822749 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 1311734 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 5037612 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 1599917 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 7084819 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 4806560 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 6514237 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 6092765 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8358. Min Act: -0.1700
Data Index: 907786 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8358. Min Act: -0.1700
Data Index: 3664043 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8671. Min Act: -0.1700
Data Index: 822369 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8358. Min Act: -0.1700
Data Index: 822372 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8358. Min Act: -0.1700
Data Index: 1311733 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9296. Min Range: -3.9296
Max Act: 3.8358. Min Act: -0.1700
Data Index: 822371 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19