Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0534. Min Range: -9.0534
Max Act: 9.0534. Min Act: -0.1700
Data Index: 8528509 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.7409. Min Act: -0.1700
Data Index: 5605578 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.4284. Min Act: -0.1700
Data Index: 6593881 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.3034. Min Act: -0.1700
Data Index: 1817241 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.1784. Min Act: -0.1700
Data Index: 5463012 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.1159. Min Act: -0.1700
Data Index: 8008744 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.1159. Min Act: -0.1700
Data Index: 7033568 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0847. Min Act: -0.1700
Data Index: 7670063 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0847. Min Act: -0.1700
Data Index: 1397566 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0534. Min Act: -0.1700
Data Index: 3539423 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0222. Min Act: -0.1700
Data Index: 6393250 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0222. Min Act: -0.1700
Data Index: 5891524 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0222. Min Act: -0.1700
Data Index: 5166412 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0222. Min Act: -0.1700
Data Index: 95916 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0534. Min Range: -9.0534
Max Act: 7.9909. Min Act: -0.1700
Data Index: 2511498 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0534. Min Range: -9.0534
Max Act: 8.0222. Min Act: -0.1700
Data Index: 7095744 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0534. Min Range: -9.0534
Max Act: 7.9597. Min Act: -0.1700
Data Index: 8183043 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0534. Min Range: -9.0534
Max Act: 7.9284. Min Act: -0.1700
Data Index: 8780907 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0534. Min Range: -9.0534
Max Act: 7.8972. Min Act: -0.1700
Data Index: 5338173 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0534. Min Range: -9.0534
Max Act: 7.8972. Min Act: -0.1700
Data Index: 8384061 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19