Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1927. Min Range: -6.1927
Max Act: 6.1927. Min Act: -0.1700
Data Index: 2165395 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1927. Min Range: -6.1927
Max Act: 6.0365. Min Act: -0.1700
Data Index: 5416488 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1927. Min Range: -6.1927
Max Act: 6.0365. Min Act: -0.1700
Data Index: 1759201 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.9740. Min Act: -0.1700
Data Index: 5116105 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8802. Min Act: -0.1699
Data Index: 2003054 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.9115. Min Act: -0.1700
Data Index: 3386868 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7309375 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7719208 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8802. Min Act: -0.1700
Data Index: 8424466 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8802. Min Act: -0.1700
Data Index: 6279936 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8802. Min Act: -0.1700
Data Index: 4186718 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8490. Min Act: -0.1700
Data Index: 2991742 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8490. Min Act: -0.1700
Data Index: 4008953 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8177. Min Act: -0.1700
Data Index: 4308570 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.8177. Min Act: -0.1700
Data Index: 3118045 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.7865. Min Act: -0.1700
Data Index: 2841759 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.7865. Min Act: -0.1700
Data Index: 8584099 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.7240. Min Act: -0.1700
Data Index: 7228532 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.7552. Min Act: -0.1700
Data Index: 5424711 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1927. Min Range: -6.1927
Max Act: 5.7240. Min Act: -0.1700
Data Index: 3679051 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19