Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6343 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.2207. Min Act: -0.1700
Data Index: 5441041 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.2207. Min Act: -0.1700
Data Index: 3688418 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 7254999 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 1580701 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 4725216 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0957. Min Act: -0.1700
Data Index: 7228589 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 2441814 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 7021645 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 138800 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0020. Min Act: -0.1700
Data Index: 4036769 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0332. Min Act: -0.1700
Data Index: 5501528 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9707. Min Act: -0.1700
Data Index: 785248 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9707. Min Act: -0.1700
Data Index: 3357857 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9395. Min Act: -0.1700
Data Index: 8256320 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1690909 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9395. Min Act: -0.1700
Data Index: 3458510 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9395. Min Act: -0.1700
Data Index: 6169109 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9082. Min Act: -0.1700
Data Index: 7557225 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9082. Min Act: -0.1700
Data Index: 2886001 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2207. Min Range: -5.2207
Max Act: 4.9082. Min Act: -0.1700
Data Index: 3057014 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19