Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 417 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0270. Min Range: -10.0270
Max Act: 10.0270. Min Act: -0.1700
Data Index: 3122616 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.9645. Min Act: -0.1700
Data Index: 1462117 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.9645. Min Act: -0.1700
Data Index: 2246707 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.7770. Min Act: -0.1700
Data Index: 5908383 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.7145. Min Act: -0.1700
Data Index: 8279381 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.7145. Min Act: -0.1700
Data Index: 7264864 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.5895. Min Act: -0.1700
Data Index: 2471647 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.5270. Min Act: -0.1700
Data Index: 3039328 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.5270. Min Act: -0.1700
Data Index: 2919986 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4645. Min Act: -0.1700
Data Index: 3657440 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4645. Min Act: -0.1700
Data Index: 3644871 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4645. Min Act: -0.1700
Data Index: 2742789 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4645. Min Act: -0.1700
Data Index: 4679386 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4645. Min Act: -0.1700
Data Index: 4547204 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4020. Min Act: -0.1700
Data Index: 6487199 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4020. Min Act: -0.1700
Data Index: 8304803 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.4020. Min Act: -0.1700
Data Index: 1668916 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.3395. Min Act: -0.1700
Data Index: 794306 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.3395. Min Act: -0.1700
Data Index: 4981088 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0270. Min Range: -10.0270
Max Act: 9.3395. Min Act: -0.1700
Data Index: 1167612 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19