Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.9831. Min Act: -0.1700
Data Index: 7966745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.8881. Min Act: -0.1700
Data Index: 6385178 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6809. Min Act: -0.1700
Data Index: 2271919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6809. Min Act: -0.1692
Data Index: 8461553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6649. Min Act: -0.1700
Data Index: 152591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6488. Min Act: -0.1700
Data Index: 7986124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6488. Min Act: -0.1699
Data Index: 5637456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6167. Min Act: -0.1700
Data Index: 267682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.6167. Min Act: -0.1700
Data Index: 8819084 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5361. Min Act: -0.1700
Data Index: 8195511 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1700
Data Index: 743768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1698
Data Index: 1453694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1700
Data Index: 7399913 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1700
Data Index: 1815324 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1699
Data Index: 7770302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1700
Data Index: 70488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1682
Data Index: 2500294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1699
Data Index: 7429412 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5200. Min Act: -0.1699
Data Index: 4800257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9831. Min Range: -2.9831
Max Act: 2.5038. Min Act: -0.1687
Data Index: 5246919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19