Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.2883. Min Act: -0.1699
Data Index: 2408919 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.2883. Min Act: -0.1700
Data Index: 1671095 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.1320. Min Act: -0.1700
Data Index: 4911743 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.1633. Min Act: -0.1700
Data Index: 4202760 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.1320. Min Act: -0.1700
Data Index: 2879569 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.1008. Min Act: -0.1700
Data Index: 63400 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.0695. Min Act: -0.1700
Data Index: 2275791 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.1008. Min Act: -0.1700
Data Index: 4157589 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.0695. Min Act: -0.1700
Data Index: 6335325 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.1008. Min Act: -0.1700
Data Index: 7893546 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.0383. Min Act: -0.1700
Data Index: 919091 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2883. Min Range: -6.2883
Max Act: 6.0695. Min Act: -0.1700
Data Index: 5394905 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 7967298 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9445. Min Act: -0.1700
Data Index: 4386416 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 669873 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 2612205 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 2353996 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 2289967 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 4375656 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2883. Min Range: -6.2883
Max Act: 5.9758. Min Act: -0.1700
Data Index: 4347797 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19