Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.7652. Min Act: -0.1700
Data Index: 4916490 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.6402. Min Act: -0.1700
Data Index: 434241 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5464. Min Act: -0.1700
Data Index: 5331816 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5464. Min Act: -0.1700
Data Index: 353363 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5464. Min Act: -0.1700
Data Index: 6192848 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5777. Min Act: -0.1700
Data Index: 8602574 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5152. Min Act: -0.1700
Data Index: 7779702 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4388998 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4508661 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4839. Min Act: -0.1700
Data Index: 922619 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4839. Min Act: -0.1700
Data Index: 3120913 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4527. Min Act: -0.1700
Data Index: 2352811 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4527. Min Act: -0.1700
Data Index: 6151071 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 4095120 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 369937 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 2635628 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 7717710 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 6295517 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 3657632 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7652. Min Range: -5.7652
Max Act: 5.4214. Min Act: -0.1700
Data Index: 538681 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19