Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4244 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.2771. Min Range: -17.2771
Max Act: 17.2771. Min Act: -0.1700
Data Index: 3989610 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.2771. Min Range: -17.2771
Max Act: 17.1521. Min Act: -0.1700
Data Index: 6903338 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.9021. Min Act: -0.1700
Data Index: 7270009 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.7771. Min Act: -0.1700
Data Index: 3224814 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 145655 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 7642638 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 3377493 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 3259399 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 3972310 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 4439306 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 5242268 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 6900880 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 6762581 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 5596236 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 7317969 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 7628162 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.4021. Min Act: -0.1700
Data Index: 3687562 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 2336079 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.6521. Min Act: -0.1700
Data Index: 2336078 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.2771. Min Range: -17.2771
Max Act: 16.5271. Min Act: -0.1700
Data Index: 3782605 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19