Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3328 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.5718. Min Act: -0.1700
Data Index: 5441516 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.6031. Min Act: -0.1700
Data Index: 6845657 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6343. Min Range: -6.6343
Max Act: 5.3531. Min Act: -0.1700
Data Index: 4193940 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.6343. Min Act: -0.1700
Data Index: 8653460 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.2593. Min Act: -0.1700
Data Index: 6444026 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.2906. Min Act: -0.1700
Data Index: 3968289 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.1968. Min Act: -0.1700
Data Index: 1598619 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6343. Min Range: -6.6343
Max Act: 5.2906. Min Act: -0.1700
Data Index: 292784 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.1031. Min Act: -0.1700
Data Index: 386442 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.1031. Min Act: -0.1700
Data Index: 1575987 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.1343. Min Act: -0.1700
Data Index: 3093938 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.0406. Min Act: -0.1700
Data Index: 371635 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.0093. Min Act: -0.1700
Data Index: 1108285 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6343. Min Range: -6.6343
Max Act: 5.6343. Min Act: -0.1700
Data Index: 4289241 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.4468. Min Act: -0.1700
Data Index: 8304107 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.0718. Min Act: -0.1700
Data Index: 4321672 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6343. Min Range: -6.6343
Max Act: 5.7593. Min Act: -0.1700
Data Index: 5437851 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.4781. Min Act: -0.1700
Data Index: 5712076 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.0406. Min Act: -0.1700
Data Index: 4065920 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6343. Min Range: -6.6343
Max Act: 6.1031. Min Act: -0.1700
Data Index: 5855803 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19