Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4627 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.6329. Min Act: -0.1700
Data Index: 871084 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.5079. Min Act: -0.1700
Data Index: 3977127 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.5079. Min Act: -0.1700
Data Index: 1205689 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.4454. Min Act: -0.1700
Data Index: 6570924 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.4142. Min Act: -0.1700
Data Index: 979116 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.4142. Min Act: -0.1700
Data Index: 5752136 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.4142. Min Act: -0.1700
Data Index: 19933 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.4142. Min Act: -0.1700
Data Index: 2589984 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 3330363 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 7459064 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 6675968 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 6071229 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3517. Min Act: -0.1700
Data Index: 1385208 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3517. Min Act: -0.1700
Data Index: 1720750 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3517. Min Act: -0.1700
Data Index: 5271244 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 2693002 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 5609227 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 3811798 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3517. Min Act: -0.1700
Data Index: 1125549 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6329. Min Range: -5.6329
Max Act: 5.3204. Min Act: -0.1700
Data Index: 5046491 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19