Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.8820. Min Act: -0.1700
Data Index: 1461676 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.5070. Min Act: -0.1700
Data Index: 5353711 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.4445. Min Act: -0.1700
Data Index: 8258997 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.3820. Min Act: -0.1700
Data Index: 558652 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.3820. Min Act: -0.1700
Data Index: 3659497 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.3195. Min Act: -0.1700
Data Index: 5406607 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.3195. Min Act: -0.1700
Data Index: 2497387 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.2570. Min Act: -0.1700
Data Index: 6220635 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.3195. Min Act: -0.1700
Data Index: 8819349 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 8473121 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 5631795 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 4995984 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 2703293 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 7522884 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 7872158 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 8037437 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 3950663 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1945. Min Act: -0.1700
Data Index: 275310 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1320. Min Act: -0.1700
Data Index: 4192098 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8820. Min Range: -8.8820
Max Act: 8.1320. Min Act: -0.1700
Data Index: 5420483 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19