Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.6757. Min Act: -0.1700
Data Index: 5223986 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.6757. Min Act: -0.1700
Data Index: 8643451 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.6757. Min Act: -0.1700
Data Index: 4466581 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.6132. Min Act: -0.1700
Data Index: 51898 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5819. Min Act: -0.1700
Data Index: 2065503 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.6132. Min Act: -0.1700
Data Index: 6974454 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5819. Min Act: -0.1700
Data Index: 2070017 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5819. Min Act: -0.1700
Data Index: 3220935 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5819. Min Act: -0.1700
Data Index: 1583140 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5194. Min Act: -0.1700
Data Index: 4530034 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5194. Min Act: -0.1700
Data Index: 949838 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5507. Min Act: -0.1700
Data Index: 7077321 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5194. Min Act: -0.1700
Data Index: 4092160 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.4882. Min Act: -0.1700
Data Index: 2274883 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5507. Min Act: -0.1700
Data Index: 455716 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.4569. Min Act: -0.1700
Data Index: 2797201 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.5194. Min Act: -0.1700
Data Index: 8068473 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.4569. Min Act: -0.1700
Data Index: 7477130 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.4882. Min Act: -0.1700
Data Index: 7127461 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6757. Min Range: -7.6757
Max Act: 7.4882. Min Act: -0.1700
Data Index: 1828786 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19