Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1579. Min Range: -10.1579
Max Act: 10.1579. Min Act: -0.1700
Data Index: 8589117 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.9704. Min Act: -0.1700
Data Index: 167858 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.9079. Min Act: -0.1700
Data Index: 1696600 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.9079. Min Act: -0.1700
Data Index: 1079260 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.7204. Min Act: -0.1700
Data Index: 7914365 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.6579. Min Act: -0.1700
Data Index: 2950648 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.4704. Min Act: -0.1700
Data Index: 3547015 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.4079. Min Act: -0.1700
Data Index: 5545138 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.4079. Min Act: -0.1700
Data Index: 7926796 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.4079. Min Act: -0.1700
Data Index: 2330576 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.3454. Min Act: -0.1700
Data Index: 2019596 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.2829. Min Act: -0.1700
Data Index: 200807 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.3454. Min Act: -0.1700
Data Index: 2710915 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.3454. Min Act: -0.1700
Data Index: 3320088 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.1579. Min Act: -0.1700
Data Index: 3709781 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.0954. Min Act: -0.1700
Data Index: 7832931 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.1579. Min Act: -0.1700
Data Index: 3571004 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.0329. Min Act: -0.1700
Data Index: 7435676 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.0954. Min Act: -0.1700
Data Index: 8057144 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1579. Min Range: -10.1579
Max Act: 9.0329. Min Act: -0.1700
Data Index: 528783 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19