Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1213. Min Range: -5.1213
Max Act: 5.1213. Min Act: -0.1700
Data Index: 2197555 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1213. Min Range: -5.1213
Max Act: 5.0275. Min Act: -0.1700
Data Index: 8276254 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.9338. Min Act: -0.1700
Data Index: 4701349 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.8400. Min Act: -0.1700
Data Index: 373671 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.7463. Min Act: -0.1700
Data Index: 5972170 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.7463. Min Act: -0.1700
Data Index: 3702908 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.7463. Min Act: -0.1700
Data Index: 3162393 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6525. Min Act: -0.1700
Data Index: 4933433 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6838. Min Act: -0.1700
Data Index: 3863094 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6838. Min Act: -0.1700
Data Index: 2197554 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6213. Min Act: -0.1700
Data Index: 7369425 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6213. Min Act: -0.1700
Data Index: 906531 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6213. Min Act: -0.1700
Data Index: 2146106 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6525. Min Act: -0.1700
Data Index: 7905662 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.6213. Min Act: -0.1700
Data Index: 3491241 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.5900. Min Act: -0.1700
Data Index: 3051667 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.5275. Min Act: -0.1700
Data Index: 654691 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.5588. Min Act: -0.1700
Data Index: 7851045 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.4963. Min Act: -0.1700
Data Index: 6249185 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1213. Min Range: -5.1213
Max Act: 4.5275. Min Act: -0.1700
Data Index: 637685 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19