Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.9375. Min Act: -0.1700
Data Index: 8701008 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.9120. Min Act: -0.1698
Data Index: 1636445 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8949. Min Act: -0.1700
Data Index: 8497614 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8864. Min Act: -0.1700
Data Index: 1853522 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8693. Min Act: -0.1697
Data Index: 8444395 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8522. Min Act: -0.1700
Data Index: 5089951 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8436. Min Act: -0.1700
Data Index: 2428433 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8265. Min Act: -0.1700
Data Index: 2118962 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8350. Min Act: -0.1700
Data Index: 400569 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8265. Min Act: -0.1700
Data Index: 2759271 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8179. Min Act: -0.1700
Data Index: 8590711 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8265. Min Act: -0.1700
Data Index: 2154615 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8265. Min Act: -0.1700
Data Index: 2730829 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8179. Min Act: -0.1700
Data Index: 475645 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8179. Min Act: -0.1699
Data Index: 1636444 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8179. Min Act: -0.1700
Data Index: 3664200 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8007. Min Act: -0.1700
Data Index: 6153522 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.8007. Min Act: -0.1700
Data Index: 1580009 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.7921. Min Act: -0.1700
Data Index: 275290 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9375. Min Range: -1.9375
Max Act: 1.7921. Min Act: -0.1700
Data Index: 6173443 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19