Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.5927. Min Act: -0.1700
Data Index: 3406600 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.5614. Min Act: -0.1700
Data Index: 4062204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.5301. Min Act: -0.1700
Data Index: 5872381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.5301. Min Act: -0.1700
Data Index: 5270638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 1611155 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 7113055 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 7101925 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 6526162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 6201795 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 5663881 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 5552805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 1691401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 5506318 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.5301. Min Act: -0.1700
Data Index: 625709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 4849296 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 4349161 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 3996333 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 3778328 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 3522087 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5927. Min Range: -3.5927
Max Act: 3.4988. Min Act: -0.1700
Data Index: 2866659 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19