Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.7804. Min Act: -0.1700
Data Index: 2185559 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4750. Min Act: -0.1700
Data Index: 3132594 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4588. Min Act: -0.1700
Data Index: 6293415 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4263. Min Act: -0.1700
Data Index: 3101339 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4425. Min Act: -0.1700
Data Index: 3935206 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4588. Min Act: -0.1700
Data Index: 5380915 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4263. Min Act: -0.1700
Data Index: 6299560 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4100. Min Act: -0.1700
Data Index: 5608754 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4100. Min Act: -0.1700
Data Index: 415086 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3936. Min Act: -0.1700
Data Index: 7914658 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4100. Min Act: -0.1700
Data Index: 5725239 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.4100. Min Act: -0.1700
Data Index: 5314170 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3936. Min Act: -0.1700
Data Index: 929742 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3936. Min Act: -0.1700
Data Index: 2996127 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3936. Min Act: -0.1700
Data Index: 4669134 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3773. Min Act: -0.1700
Data Index: 3638915 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3773. Min Act: -0.1700
Data Index: 6434413 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3609. Min Act: -0.1700
Data Index: 1085076 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3773. Min Act: -0.1700
Data Index: 4011571 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7804. Min Range: -2.7804
Max Act: 2.3609. Min Act: -0.1700
Data Index: 734682 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19