Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1717 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.4611. Min Act: -0.1700
Data Index: 6134141 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.2111. Min Act: -0.1700
Data Index: 6298546 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.1799. Min Act: -0.1700
Data Index: 5479211 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.1174. Min Act: -0.1700
Data Index: 232792 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.1174. Min Act: -0.1700
Data Index: 7920967 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.9299. Min Act: -0.1700
Data Index: 6014985 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8674. Min Act: -0.1700
Data Index: 3173276 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8361. Min Act: -0.1700
Data Index: 795532 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8049. Min Act: -0.1700
Data Index: 6648556 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7424. Min Act: -0.1700
Data Index: 2129406 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7424. Min Act: -0.1700
Data Index: 76940 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7111. Min Act: -0.1700
Data Index: 4592380 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7111. Min Act: -0.1700
Data Index: 524921 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7111. Min Act: -0.1700
Data Index: 4770553 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7111. Min Act: -0.1700
Data Index: 8608570 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6799. Min Act: -0.1700
Data Index: 8084746 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6799. Min Act: -0.1700
Data Index: 5421915 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 47981 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 6921448 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 8416184 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19