Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.8049. Min Act: -0.1700
Data Index: 3648724 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.2737. Min Act: -0.1700
Data Index: 5159551 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.1799. Min Act: -0.1700
Data Index: 7192245 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.1487. Min Act: -0.1700
Data Index: 5206283 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.1487. Min Act: -0.1700
Data Index: 4656182 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.1487. Min Act: -0.1700
Data Index: 4520887 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.0549. Min Act: -0.1700
Data Index: 5434843 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.0862. Min Act: -0.1700
Data Index: 1470955 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.0862. Min Act: -0.1700
Data Index: 6279415 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.0549. Min Act: -0.1700
Data Index: 355110 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.0549. Min Act: -0.1700
Data Index: 5836591 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8049. Min Range: -7.8049
Max Act: 7.0237. Min Act: -0.1700
Data Index: 5850693 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9924. Min Act: -0.1700
Data Index: 3440925 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9924. Min Act: -0.1700
Data Index: 44968 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9612. Min Act: -0.1700
Data Index: 3798446 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9612. Min Act: -0.1700
Data Index: 6885010 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9299. Min Act: -0.1700
Data Index: 3526763 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9612. Min Act: -0.1700
Data Index: 1313348 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9612. Min Act: -0.1700
Data Index: 1843030 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8049. Min Range: -7.8049
Max Act: 6.9612. Min Act: -0.1700
Data Index: 1272023 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19