Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.6613. Min Act: -0.1700
Data Index: 1123402 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.6613. Min Act: -0.1700
Data Index: 2966861 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.6301. Min Act: -0.1700
Data Index: 3009121 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.5676. Min Act: -0.1700
Data Index: 5766886 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.5676. Min Act: -0.1700
Data Index: 4305694 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.4113. Min Act: -0.1700
Data Index: 987714 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.3801. Min Act: -0.1700
Data Index: 5003917 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.3488. Min Act: -0.1700
Data Index: 8379937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.3176. Min Act: -0.1700
Data Index: 5283690 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2863. Min Act: -0.1700
Data Index: 3548366 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2863. Min Act: -0.1700
Data Index: 2462926 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2863. Min Act: -0.1700
Data Index: 75902 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2238. Min Act: -0.1700
Data Index: 2512854 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 8210740 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 3363086 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 6484221 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 6975586 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 4752497 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 1350024 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6613. Min Range: -4.6613
Max Act: 4.2551. Min Act: -0.1700
Data Index: 6061499 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19