Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.8891. Min Act: -0.1700
Data Index: 4496765 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.8733. Min Act: -0.1700
Data Index: 5395814 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.8733. Min Act: -0.1700
Data Index: 2148916 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.8256. Min Act: -0.1700
Data Index: 2465830 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.8256. Min Act: -0.1700
Data Index: 7012365 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.8097. Min Act: -0.1700
Data Index: 1626108 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7938. Min Act: -0.1700
Data Index: 2507989 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7778. Min Act: -0.1700
Data Index: 3337814 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7778. Min Act: -0.1700
Data Index: 430742 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7619. Min Act: -0.1700
Data Index: 6352640 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7619. Min Act: -0.1700
Data Index: 5950746 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7619. Min Act: -0.1700
Data Index: 3797252 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7619. Min Act: -0.1700
Data Index: 229930 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7619. Min Act: -0.1700
Data Index: 2864697 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7300. Min Act: -0.1700
Data Index: 6642110 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7459. Min Act: -0.1700
Data Index: 2797825 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7459. Min Act: -0.1700
Data Index: 7691646 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7459. Min Act: -0.1700
Data Index: 80210 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7459. Min Act: -0.1700
Data Index: 6297561 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8891. Min Range: -2.8891
Max Act: 2.7459. Min Act: -0.1700
Data Index: 3905310 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19