Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2611. Min Range: -6.2611
Max Act: 6.2611. Min Act: -0.1700
Data Index: 3079665 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2611. Min Range: -6.2611
Max Act: 6.1674. Min Act: -0.1700
Data Index: 8066364 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2611. Min Range: -6.2611
Max Act: 6.1049. Min Act: -0.1700
Data Index: 270331 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2611. Min Range: -6.2611
Max Act: 6.0424. Min Act: -0.1700
Data Index: 7602729 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2611. Min Range: -6.2611
Max Act: 6.0111. Min Act: -0.1700
Data Index: 4023760 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.9799. Min Act: -0.1700
Data Index: 8052250 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.9486. Min Act: -0.1700
Data Index: 5285072 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.9174. Min Act: -0.1700
Data Index: 1736038 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.9174. Min Act: -0.1700
Data Index: 5472425 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.8861. Min Act: -0.1700
Data Index: 3082004 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.8861. Min Act: -0.1700
Data Index: 6131449 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.8861. Min Act: -0.1700
Data Index: 1249704 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.8236. Min Act: -0.1700
Data Index: 2158987 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.8236. Min Act: -0.1700
Data Index: 3404987 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.7924. Min Act: -0.1700
Data Index: 4288692 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.7924. Min Act: -0.1700
Data Index: 1677213 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.7611. Min Act: -0.1700
Data Index: 5326721 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.7611. Min Act: -0.1700
Data Index: 947671 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.7611. Min Act: -0.1700
Data Index: 6842692 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2611. Min Range: -6.2611
Max Act: 5.7299. Min Act: -0.1700
Data Index: 556088 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19