Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2206 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.3681. Min Act: -0.1700
Data Index: 6603386 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.2744. Min Act: -0.1700
Data Index: 7452074 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.2431. Min Act: -0.1700
Data Index: 8267310 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.2431. Min Act: -0.1700
Data Index: 3004031 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.1181. Min Act: -0.1700
Data Index: 319747 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.0556. Min Act: -0.1700
Data Index: 6053389 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.0244. Min Act: -0.1700
Data Index: 1033746 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.9931. Min Act: -0.1700
Data Index: 483648 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3681. Min Range: -5.3681
Max Act: 5.0244. Min Act: -0.1700
Data Index: 6411962 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.9619. Min Act: -0.1700
Data Index: 125723 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.9619. Min Act: -0.1700
Data Index: 6151266 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8994. Min Act: -0.1700
Data Index: 722420 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.9306. Min Act: -0.1700
Data Index: 618936 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8994. Min Act: -0.1700
Data Index: 5977740 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8681. Min Act: -0.1700
Data Index: 2154567 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8994. Min Act: -0.1700
Data Index: 6439784 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8369. Min Act: -0.1700
Data Index: 960990 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8681. Min Act: -0.1700
Data Index: 6020957 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8369. Min Act: -0.1700
Data Index: 4267162 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3681. Min Range: -5.3681
Max Act: 4.8681. Min Act: -0.1700
Data Index: 3152765 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19