Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.9406. Min Act: -0.1700
Data Index: 6724157 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.8781. Min Act: -0.1700
Data Index: 5412909 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.8781. Min Act: -0.1700
Data Index: 6206150 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6906. Min Act: -0.1700
Data Index: 3334266 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6906. Min Act: -0.1700
Data Index: 6898671 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6594. Min Act: -0.1700
Data Index: 5453379 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6906. Min Act: -0.1700
Data Index: 6075837 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6906. Min Act: -0.1700
Data Index: 73152 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6906. Min Act: -0.1700
Data Index: 2308945 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6594. Min Act: -0.1700
Data Index: 3892998 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6281. Min Act: -0.1700
Data Index: 6678626 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6906. Min Act: -0.1700
Data Index: 5509389 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6594. Min Act: -0.1700
Data Index: 1759558 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6594. Min Act: -0.1700
Data Index: 2202922 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.5969. Min Act: -0.1700
Data Index: 6983960 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.5969. Min Act: -0.1700
Data Index: 2484923 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.6281. Min Act: -0.1700
Data Index: 4067452 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.5969. Min Act: -0.1700
Data Index: 3199136 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.5656. Min Act: -0.1700
Data Index: 6220467 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9406. Min Range: -6.9406
Max Act: 6.5656. Min Act: -0.1700
Data Index: 5425329 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19