Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.8993. Min Act: -0.1700
Data Index: 1621490 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.8368. Min Act: -0.1700
Data Index: 4608741 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8993. Min Range: -8.8993
Max Act: 6.7431. Min Act: -0.1700
Data Index: 2734048 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.3368. Min Act: -0.1700
Data Index: 7312637 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.7743. Min Act: -0.1700
Data Index: 6516980 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.7118. Min Act: -0.1700
Data Index: 5545049 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.7431. Min Act: -0.1700
Data Index: 7507854 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.5868. Min Act: -0.1700
Data Index: 7507849 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.2118. Min Act: -0.1699
Data Index: 7507857 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.0243. Min Act: -0.1700
Data Index: 8345586 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.1493. Min Act: -0.1700
Data Index: 1637551 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8993. Min Range: -8.8993
Max Act: 8.0868. Min Act: -0.1700
Data Index: 3031861 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8993. Min Range: -8.8993
Max Act: 4.8368. Min Act: -0.1700
Data Index: 111993 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.9618. Min Act: -0.1699
Data Index: 5582364 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.1493. Min Act: -0.1700
Data Index: 1739106 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.9618. Min Act: -0.1700
Data Index: 6516979 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.8993. Min Act: -0.1700
Data Index: 4815848 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.8368. Min Act: -0.1700
Data Index: 1754705 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.6493. Min Act: -0.1700
Data Index: 3998962 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8993. Min Range: -8.8993
Max Act: 7.8993. Min Act: -0.1700
Data Index: 784365 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19