Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.9873. Min Act: -0.1700
Data Index: 975683 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.8623. Min Act: -0.1700
Data Index: 7182974 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.7998. Min Act: -0.1700
Data Index: 5161980 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.7998. Min Act: -0.1700
Data Index: 1174286 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.7998. Min Act: -0.1700
Data Index: 7327385 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.7373. Min Act: -0.1700
Data Index: 354282 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.7373. Min Act: -0.1700
Data Index: 4474709 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6748. Min Act: -0.1700
Data Index: 1780098 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.7373. Min Act: -0.1700
Data Index: 1780099 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6748. Min Act: -0.1700
Data Index: 3778062 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6436. Min Act: -0.1700
Data Index: 1833582 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6436. Min Act: -0.1700
Data Index: 16552 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6436. Min Act: -0.1700
Data Index: 2422820 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6436. Min Act: -0.1700
Data Index: 1328152 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6123. Min Act: -0.1700
Data Index: 483508 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6123. Min Act: -0.1700
Data Index: 4646655 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6123. Min Act: -0.1700
Data Index: 804386 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6123. Min Act: -0.1700
Data Index: 5468833 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.6123. Min Act: -0.1700
Data Index: 4269005 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9873. Min Range: -4.9873
Max Act: 4.5811. Min Act: -0.1700
Data Index: 2000871 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19