Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.8304. Min Act: -0.1700
Data Index: 7567247 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.7992. Min Act: -0.1700
Data Index: 3399487 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2054207 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6742. Min Act: -0.1700
Data Index: 181478 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6742. Min Act: -0.1700
Data Index: 1253188 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6429. Min Act: -0.1700
Data Index: 5507777 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6429. Min Act: -0.1700
Data Index: 5965844 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6429. Min Act: -0.1700
Data Index: 4171729 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2491042 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6117. Min Act: -0.1700
Data Index: 785672 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.6117. Min Act: -0.1700
Data Index: 829673 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5804. Min Act: -0.1700
Data Index: 1395345 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5804. Min Act: -0.1700
Data Index: 3097645 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5804. Min Act: -0.1700
Data Index: 7925019 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5492. Min Act: -0.1700
Data Index: 3822833 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5492. Min Act: -0.1700
Data Index: 946519 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5492. Min Act: -0.1700
Data Index: 7688676 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5179. Min Act: -0.1700
Data Index: 1435747 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4322838 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8304. Min Range: -5.8304
Max Act: 5.5179. Min Act: -0.1700
Data Index: 1989789 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19