Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1629 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2728. Min Range: -7.2728
Max Act: 7.2728. Min Act: -0.1700
Data Index: 7612367 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2728. Min Range: -7.2728
Max Act: 7.2415. Min Act: -0.1700
Data Index: 6876448 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2728. Min Range: -7.2728
Max Act: 7.1478. Min Act: -0.1700
Data Index: 609605 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2728. Min Range: -7.2728
Max Act: 7.0853. Min Act: -0.1700
Data Index: 8779347 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2728. Min Range: -7.2728
Max Act: 7.0853. Min Act: -0.1700
Data Index: 6311128 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2728. Min Range: -7.2728
Max Act: 7.0540. Min Act: -0.1700
Data Index: 3408452 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.9915. Min Act: -0.1700
Data Index: 6880211 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.9290. Min Act: -0.1700
Data Index: 6284227 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.8978. Min Act: -0.1700
Data Index: 1968394 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.8978. Min Act: -0.1700
Data Index: 3216663 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.8353. Min Act: -0.1700
Data Index: 3061126 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.8040. Min Act: -0.1700
Data Index: 2516793 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7728. Min Act: -0.1700
Data Index: 5786711 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7415. Min Act: -0.1700
Data Index: 4636559 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7728. Min Act: -0.1700
Data Index: 5637324 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7415. Min Act: -0.1700
Data Index: 1329579 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7415. Min Act: -0.1700
Data Index: 2273355 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7103. Min Act: -0.1700
Data Index: 2269033 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.7103. Min Act: -0.1700
Data Index: 1701227 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2728. Min Range: -7.2728
Max Act: 6.6790. Min Act: -0.1700
Data Index: 241731 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19