Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.8048. Min Act: -0.1700
Data Index: 3195218 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.6798. Min Act: -0.1700
Data Index: 2877171 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.5548. Min Act: -0.1700
Data Index: 2333280 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.4923. Min Act: -0.1700
Data Index: 1791693 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.4923. Min Act: -0.1700
Data Index: 7377490 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.3673. Min Act: -0.1700
Data Index: 951526 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.4298. Min Act: -0.1700
Data Index: 333170 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.3673. Min Act: -0.1700
Data Index: 1248384 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.3048. Min Act: -0.1700
Data Index: 5099101 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.3048. Min Act: -0.1700
Data Index: 2072282 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.2423. Min Act: -0.1700
Data Index: 5100323 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1798. Min Act: -0.1700
Data Index: 7762987 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1173. Min Act: -0.1700
Data Index: 6300260 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1173. Min Act: -0.1700
Data Index: 8800756 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1173. Min Act: -0.1700
Data Index: 7068832 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1173. Min Act: -0.1700
Data Index: 7527802 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1173. Min Act: -0.1700
Data Index: 4354600 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8048. Min Range: -9.8048
Max Act: 9.1173. Min Act: -0.1700
Data Index: 2464560 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8048. Min Range: -9.8048
Max Act: 8.9298. Min Act: -0.1700
Data Index: 3990588 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8048. Min Range: -9.8048
Max Act: 8.9923. Min Act: -0.1700
Data Index: 3833497 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19