Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.5411. Min Act: -0.1700
Data Index: 767444 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.5099. Min Act: -0.1700
Data Index: 6495752 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.5099. Min Act: -0.1700
Data Index: 4296383 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4474. Min Act: -0.1700
Data Index: 4489274 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4786. Min Act: -0.1700
Data Index: 7364846 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4786. Min Act: -0.1700
Data Index: 125154 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4786. Min Act: -0.1700
Data Index: 7225517 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4786. Min Act: -0.1700
Data Index: 4692594 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4474. Min Act: -0.1700
Data Index: 1271770 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4786. Min Act: -0.1700
Data Index: 2699592 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4474. Min Act: -0.1700
Data Index: 8550051 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4474. Min Act: -0.1700
Data Index: 6787792 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4474. Min Act: -0.1700
Data Index: 5081942 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4474. Min Act: -0.1700
Data Index: 700752 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4161. Min Act: -0.1700
Data Index: 53038 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4161. Min Act: -0.1700
Data Index: 1355029 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4161. Min Act: -0.1700
Data Index: 6531665 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4161. Min Act: -0.1700
Data Index: 5163025 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4161. Min Act: -0.1700
Data Index: 5187799 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.4161. Min Act: -0.1700
Data Index: 3321728 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19