Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.5717. Min Act: -0.1700
Data Index: 2185971 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.2592. Min Act: -0.1700
Data Index: 486689 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.1654. Min Act: -0.1700
Data Index: 3145676 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.1967. Min Act: -0.1700
Data Index: 5568041 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.1342. Min Act: -0.1700
Data Index: 2837707 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.1029. Min Act: -0.1700
Data Index: 1461855 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.1029. Min Act: -0.1700
Data Index: 1499971 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5717. Min Range: -8.5717
Max Act: 8.0404. Min Act: -0.1700
Data Index: 3641 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.9779. Min Act: -0.1700
Data Index: 4436342 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.9779. Min Act: -0.1700
Data Index: 2627152 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.9467. Min Act: -0.1700
Data Index: 7515646 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.9467. Min Act: -0.1700
Data Index: 1460340 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.9154. Min Act: -0.1700
Data Index: 3457386 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.8842. Min Act: -0.1700
Data Index: 2030781 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.8217. Min Act: -0.1700
Data Index: 2019788 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.8842. Min Act: -0.1700
Data Index: 2493030 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.7279. Min Act: -0.1700
Data Index: 1046914 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.7279. Min Act: -0.1700
Data Index: 7003562 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.6967. Min Act: -0.1700
Data Index: 5883423 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5717. Min Range: -8.5717
Max Act: 7.7279. Min Act: -0.1700
Data Index: 3495209 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19