Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1278. Min Range: -6.1278
Max Act: 6.1278. Min Act: -0.1700
Data Index: 748178 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1278. Min Range: -6.1278
Max Act: 6.0341. Min Act: -0.1700
Data Index: 1933646 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.8778. Min Act: -0.1700
Data Index: 5575826 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.8778. Min Act: -0.1700
Data Index: 7342478 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.8466. Min Act: -0.1700
Data Index: 1564692 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.8466. Min Act: -0.1700
Data Index: 2081577 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.7841. Min Act: -0.1700
Data Index: 7952616 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.7841. Min Act: -0.1700
Data Index: 6969011 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.7841. Min Act: -0.1700
Data Index: 6742019 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.7216. Min Act: -0.1700
Data Index: 6849967 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.7528. Min Act: -0.1700
Data Index: 3984581 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.6903. Min Act: -0.1700
Data Index: 6054264 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.6903. Min Act: -0.1700
Data Index: 551383 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.6591. Min Act: -0.1700
Data Index: 8617900 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.6591. Min Act: -0.1700
Data Index: 3148180 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.5966. Min Act: -0.1700
Data Index: 2903460 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.6278. Min Act: -0.1700
Data Index: 6515322 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.5966. Min Act: -0.1700
Data Index: 1996317 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.5966. Min Act: -0.1700
Data Index: 4947382 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1278. Min Range: -6.1278
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3597020 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19