Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0635. Min Range: -5.0635
Max Act: 5.0635. Min Act: -0.1700
Data Index: 8512417 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.8760. Min Act: -0.1700
Data Index: 1069335 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.9073. Min Act: -0.1700
Data Index: 8561800 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.8448. Min Act: -0.1700
Data Index: 4029703 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.8448. Min Act: -0.1700
Data Index: 6253197 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.7510. Min Act: -0.1700
Data Index: 8152441 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.6885. Min Act: -0.1700
Data Index: 1616073 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.6573. Min Act: -0.1700
Data Index: 5130641 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5948. Min Act: -0.1700
Data Index: 5870621 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.6260. Min Act: -0.1700
Data Index: 4923908 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5948. Min Act: -0.1700
Data Index: 4660233 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.6260. Min Act: -0.1700
Data Index: 918924 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.6260. Min Act: -0.1700
Data Index: 4925838 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5323. Min Act: -0.1700
Data Index: 5851704 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5635. Min Act: -0.1700
Data Index: 5993111 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5323. Min Act: -0.1700
Data Index: 7881759 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5010. Min Act: -0.1700
Data Index: 730166 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5323. Min Act: -0.1700
Data Index: 2195629 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5010. Min Act: -0.1700
Data Index: 8705374 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0635. Min Range: -5.0635
Max Act: 4.5010. Min Act: -0.1700
Data Index: 7936265 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19