Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.3484. Min Act: -0.1700
Data Index: 8505229 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.3172. Min Act: -0.1700
Data Index: 4070919 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.2859. Min Act: -0.1700
Data Index: 7519421 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.2547. Min Act: -0.1700
Data Index: 7904028 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.2234. Min Act: -0.1700
Data Index: 8818477 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1922. Min Act: -0.1700
Data Index: 5626393 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.2234. Min Act: -0.1700
Data Index: 5641921 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1922. Min Act: -0.1700
Data Index: 4968416 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1922. Min Act: -0.1700
Data Index: 4872759 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1922. Min Act: -0.1700
Data Index: 2467357 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1609. Min Act: -0.1700
Data Index: 625778 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1609. Min Act: -0.1700
Data Index: 1083909 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1609. Min Act: -0.1700
Data Index: 5272229 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1609. Min Act: -0.1700
Data Index: 317101 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1609. Min Act: -0.1700
Data Index: 5505425 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1297. Min Act: -0.1700
Data Index: 4962616 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6085163 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1297. Min Act: -0.1700
Data Index: 2187524 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.1297. Min Act: -0.1700
Data Index: 3207669 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3484. Min Range: -5.3484
Max Act: 5.0984. Min Act: -0.1700
Data Index: 5402484 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19