Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0514. Min Range: -5.0514
Max Act: 5.0514. Min Act: -0.1700
Data Index: 6655562 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.6452. Min Act: -0.1700
Data Index: 362696 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.6139. Min Act: -0.1700
Data Index: 5909446 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.6139. Min Act: -0.1700
Data Index: 6242004 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.5514. Min Act: -0.1700
Data Index: 7467098 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.4577. Min Act: -0.1700
Data Index: 1709991 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.4577. Min Act: -0.1700
Data Index: 3360550 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.4264. Min Act: -0.1700
Data Index: 2321140 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.4577. Min Act: -0.1700
Data Index: 1180932 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.4577. Min Act: -0.1700
Data Index: 4135425 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3639. Min Act: -0.1700
Data Index: 118533 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3951. Min Act: -0.1700
Data Index: 8521698 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3639. Min Act: -0.1700
Data Index: 6391952 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3326. Min Act: -0.1700
Data Index: 7926736 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3639. Min Act: -0.1700
Data Index: 8170324 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3326. Min Act: -0.1700
Data Index: 2513971 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3014. Min Act: -0.1700
Data Index: 7494910 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.3014. Min Act: -0.1700
Data Index: 6491063 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.2389. Min Act: -0.1700
Data Index: 6777863 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0514. Min Range: -5.0514
Max Act: 4.2701. Min Act: -0.1700
Data Index: 234325 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19