Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0611. Min Range: -5.0611
Max Act: 5.0611. Min Act: -0.1700
Data Index: 2926681 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.9361. Min Act: -0.1700
Data Index: 7662667 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 7420256 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.9361. Min Act: -0.1700
Data Index: 1295566 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.8736. Min Act: -0.1700
Data Index: 5064965 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.8423. Min Act: -0.1700
Data Index: 114916 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.8736. Min Act: -0.1700
Data Index: 8336916 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.8111. Min Act: -0.1700
Data Index: 6370655 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.8423. Min Act: -0.1700
Data Index: 641324 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7798. Min Act: -0.1700
Data Index: 2113500 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7798. Min Act: -0.1700
Data Index: 3843804 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7798. Min Act: -0.1700
Data Index: 6917189 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7798. Min Act: -0.1700
Data Index: 8631598 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7798. Min Act: -0.1700
Data Index: 3891849 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7486. Min Act: -0.1700
Data Index: 7745335 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7486. Min Act: -0.1700
Data Index: 5719413 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7173. Min Act: -0.1700
Data Index: 6117967 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.7173. Min Act: -0.1700
Data Index: 4403229 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.6861. Min Act: -0.1700
Data Index: 3154095 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0611. Min Range: -5.0611
Max Act: 4.6861. Min Act: -0.1700
Data Index: 366008 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19