Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0127. Min Range: -5.0127
Max Act: 5.0127. Min Act: -0.1700
Data Index: 8575296 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.9190. Min Act: -0.1700
Data Index: 4583971 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.8877. Min Act: -0.1700
Data Index: 8526010 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.8565. Min Act: -0.1700
Data Index: 7582946 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.8565. Min Act: -0.1700
Data Index: 5760395 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7940. Min Act: -0.1700
Data Index: 490481 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7627. Min Act: -0.1700
Data Index: 4598771 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7940. Min Act: -0.1700
Data Index: 4916339 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7940. Min Act: -0.1700
Data Index: 2413176 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7627. Min Act: -0.1700
Data Index: 6335643 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7627. Min Act: -0.1700
Data Index: 8715997 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7627. Min Act: -0.1700
Data Index: 5586011 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7315. Min Act: -0.1700
Data Index: 7205015 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7315. Min Act: -0.1700
Data Index: 5884583 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7315. Min Act: -0.1700
Data Index: 4050208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7315. Min Act: -0.1700
Data Index: 8247305 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7002. Min Act: -0.1700
Data Index: 1206043 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7002. Min Act: -0.1700
Data Index: 7129104 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.6690. Min Act: -0.1700
Data Index: 7608355 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0127. Min Range: -5.0127
Max Act: 4.7002. Min Act: -0.1700
Data Index: 7731668 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19