Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.9791. Min Act: -0.1700
Data Index: 3260911 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.6979. Min Act: -0.1700
Data Index: 1873759 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.6979. Min Act: -0.1700
Data Index: 7391851 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.6666. Min Act: -0.1700
Data Index: 966855 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.6041. Min Act: -0.1700
Data Index: 6334342 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.6041. Min Act: -0.1700
Data Index: 6839667 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.5416. Min Act: -0.1700
Data Index: 1803561 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.5729. Min Act: -0.1700
Data Index: 5533038 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.5416. Min Act: -0.1700
Data Index: 7471806 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.5104. Min Act: -0.1700
Data Index: 242040 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.5416. Min Act: -0.1700
Data Index: 844200 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4791. Min Act: -0.1700
Data Index: 2949441 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4791. Min Act: -0.1700
Data Index: 2404952 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4791. Min Act: -0.1700
Data Index: 7672674 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4479. Min Act: -0.1700
Data Index: 1887907 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4479. Min Act: -0.1700
Data Index: 7058067 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4166. Min Act: -0.1700
Data Index: 5621926 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.4166. Min Act: -0.1700
Data Index: 3376202 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.3541. Min Act: -0.1700
Data Index: 697765 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9791. Min Range: -5.9791
Max Act: 5.3854. Min Act: -0.1700
Data Index: 905625 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19