Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.2331. Min Act: -0.1700
Data Index: 6451904 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.2018. Min Act: -0.1700
Data Index: 383903 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.2018. Min Act: -0.1700
Data Index: 776427 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.2018. Min Act: -0.1700
Data Index: 7811554 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.2018. Min Act: -0.1700
Data Index: 273086 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.1706. Min Act: -0.1700
Data Index: 5146513 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.1706. Min Act: -0.1700
Data Index: 6036967 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.1393. Min Act: -0.1700
Data Index: 4065390 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.1081. Min Act: -0.1700
Data Index: 2616927 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.1081. Min Act: -0.1700
Data Index: 8763650 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0768. Min Act: -0.1700
Data Index: 6726222 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0768. Min Act: -0.1700
Data Index: 8371723 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 7860289 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 4800066 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 2427409 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 5515735 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0143. Min Act: -0.1700
Data Index: 1041943 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0143. Min Act: -0.1700
Data Index: 6188268 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 1472084 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0143. Min Act: -0.1700
Data Index: 727916 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19