Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2217. Min Range: -7.2217
Max Act: 7.2217. Min Act: -0.1700
Data Index: 2797214 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.5030. Min Act: -0.1700
Data Index: 6002391 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.4092. Min Act: -0.1700
Data Index: 386958 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.3467. Min Act: -0.1700
Data Index: 6390420 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.3467. Min Act: -0.1700
Data Index: 386955 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.2530. Min Act: -0.1700
Data Index: 8280459 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.2530. Min Act: -0.1700
Data Index: 8455657 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1905. Min Act: -0.1700
Data Index: 251045 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1905. Min Act: -0.1700
Data Index: 6105627 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.2217. Min Act: -0.1700
Data Index: 1768144 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1592. Min Act: -0.1700
Data Index: 6557096 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1592. Min Act: -0.1700
Data Index: 1082567 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1592. Min Act: -0.1700
Data Index: 1043729 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 468923 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 6762959 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 6920858 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.0655. Min Act: -0.1700
Data Index: 8552147 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.0655. Min Act: -0.1700
Data Index: 896913 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.0655. Min Act: -0.1700
Data Index: 6590336 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2217. Min Range: -7.2217
Max Act: 6.0030. Min Act: -0.1700
Data Index: 5254312 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19