Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.3059. Min Act: -0.1700
Data Index: 6184340 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.2565. Min Act: -0.1700
Data Index: 7234039 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.2565. Min Act: -0.1700
Data Index: 7084838 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.2069. Min Act: -0.1700
Data Index: 2096185 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1737. Min Act: -0.1700
Data Index: 1159197 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1903. Min Act: -0.1700
Data Index: 2163811 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1570. Min Act: -0.1700
Data Index: 6313065 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1570. Min Act: -0.1700
Data Index: 2106645 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1737. Min Act: -0.1700
Data Index: 3932627 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1403. Min Act: -0.1700
Data Index: 1103032 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1403. Min Act: -0.1700
Data Index: 7830233 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1403. Min Act: -0.1700
Data Index: 6959692 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1737. Min Act: -0.1700
Data Index: 6093004 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1236. Min Act: -0.1700
Data Index: 1605671 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1403. Min Act: -0.1700
Data Index: 6569926 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1236. Min Act: -0.1700
Data Index: 6229686 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1236. Min Act: -0.1700
Data Index: 1364714 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1403. Min Act: -0.1700
Data Index: 4887674 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1236. Min Act: -0.1700
Data Index: 5905102 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3059. Min Range: -2.3059
Max Act: 2.1069. Min Act: -0.1700
Data Index: 4444510 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19