Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 431 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6824. Min Act: -0.1700
Data Index: 340079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6824. Min Act: -0.1700
Data Index: 3953428 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6824. Min Act: -0.1700
Data Index: 5549954 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6511. Min Act: -0.1700
Data Index: 3928258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 6183993 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 8269246 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 6073673 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 5998728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 7770916 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 8398173 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 43896 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 8320706 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 8320703 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 3074781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.6198. Min Act: -0.1700
Data Index: 4052350 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.5885. Min Act: -0.1700
Data Index: 4371653 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.5885. Min Act: -0.1700
Data Index: 107618 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.5885. Min Act: -0.1700
Data Index: 7909316 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.5885. Min Act: -0.1700
Data Index: 2671793 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6824. Min Range: -3.6824
Max Act: 3.5885. Min Act: -0.1700
Data Index: 8034715 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19