Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0081. Min Range: -9.0081
Max Act: 9.0081. Min Act: -0.1700
Data Index: 8108352 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.6331. Min Act: -0.1700
Data Index: 5542591 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.7581. Min Act: -0.1700
Data Index: 7430471 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.6956. Min Act: -0.1700
Data Index: 4990833 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.6331. Min Act: -0.1700
Data Index: 1200822 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.6331. Min Act: -0.1700
Data Index: 2567067 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.5706. Min Act: -0.1700
Data Index: 5850 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.5081. Min Act: -0.1700
Data Index: 5835084 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.5081. Min Act: -0.1700
Data Index: 5275604 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.5081. Min Act: -0.1700
Data Index: 7682473 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.5081. Min Act: -0.1700
Data Index: 6627773 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.4456. Min Act: -0.1700
Data Index: 1215650 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3831. Min Act: -0.1700
Data Index: 717382 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.4456. Min Act: -0.1700
Data Index: 814407 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3206. Min Act: -0.1700
Data Index: 3346694 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3206. Min Act: -0.1700
Data Index: 2059153 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3206. Min Act: -0.1700
Data Index: 4461679 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3206. Min Act: -0.1700
Data Index: 3329581 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3206. Min Act: -0.1700
Data Index: 3168878 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0081. Min Range: -9.0081
Max Act: 8.3206. Min Act: -0.1700
Data Index: 6554330 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19