Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.4238. Min Act: -0.1700
Data Index: 3991071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3613. Min Act: -0.1700
Data Index: 4229132 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3613. Min Act: -0.1700
Data Index: 5341071 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3301. Min Act: -0.1700
Data Index: 2338281 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2363. Min Act: -0.1700
Data Index: 412531 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2051. Min Act: -0.1700
Data Index: 5722554 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2051. Min Act: -0.1700
Data Index: 1724235 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1738. Min Act: -0.1700
Data Index: 8617605 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1738. Min Act: -0.1700
Data Index: 5936282 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1738. Min Act: -0.1700
Data Index: 4713724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1738. Min Act: -0.1700
Data Index: 7592253 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1738. Min Act: -0.1700
Data Index: 7927241 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1738. Min Act: -0.1700
Data Index: 1943666 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 5224031 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 111665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1827247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 6857350 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 4157398 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 5834930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0801. Min Act: -0.1700
Data Index: 5383773 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19