Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 644 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.6020. Min Act: -0.1700
Data Index: 6216872 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.5395. Min Act: -0.1700
Data Index: 4087091 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.4145. Min Act: -0.1700
Data Index: 1635630 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.3520. Min Act: -0.1700
Data Index: 8553359 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2895. Min Act: -0.1700
Data Index: 6169741 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2895. Min Act: -0.1700
Data Index: 349932 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2895. Min Act: -0.1700
Data Index: 1936532 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.3520. Min Act: -0.1700
Data Index: 6114256 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2895. Min Act: -0.1700
Data Index: 1835146 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2895. Min Act: -0.1700
Data Index: 5829108 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2270. Min Act: -0.1700
Data Index: 738354 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2270. Min Act: -0.1700
Data Index: 1267524 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2895. Min Act: -0.1700
Data Index: 1563425 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2270. Min Act: -0.1700
Data Index: 204673 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.2270. Min Act: -0.1700
Data Index: 408280 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.1645. Min Act: -0.1700
Data Index: 4228700 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.1645. Min Act: -0.1700
Data Index: 5313628 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.0707. Min Act: -0.1700
Data Index: 6522466 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.1020. Min Act: -0.1700
Data Index: 5859555 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6020. Min Range: -8.6020
Max Act: 8.1020. Min Act: -0.1700
Data Index: 4951924 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19