Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.7803. Min Act: -0.1700
Data Index: 8521662 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.6553. Min Act: -0.1700
Data Index: 2839424 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.6553. Min Act: -0.1700
Data Index: 8814218 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.5928. Min Act: -0.1700
Data Index: 4215698 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.5928. Min Act: -0.1700
Data Index: 5820205 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.5303. Min Act: -0.1700
Data Index: 8764869 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4990. Min Act: -0.1700
Data Index: 5389243 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4678. Min Act: -0.1700
Data Index: 3867377 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4365. Min Act: -0.1700
Data Index: 8320915 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4365. Min Act: -0.1700
Data Index: 2250491 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4365. Min Act: -0.1700
Data Index: 8317564 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4053. Min Act: -0.1700
Data Index: 7794180 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3904798 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3865448 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.3740. Min Act: -0.1700
Data Index: 4891696 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.3740. Min Act: -0.1700
Data Index: 522976 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.3428. Min Act: -0.1700
Data Index: 3040088 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.3740. Min Act: -0.1700
Data Index: 272512 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.3740. Min Act: -0.1700
Data Index: 2389172 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7803. Min Range: -5.7803
Max Act: 5.3428. Min Act: -0.1700
Data Index: 8513143 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19