Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1905 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.2485. Min Range: -7.2485
Max Act: 7.2485. Min Act: -0.1700
Data Index: 2626299 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.9048. Min Act: -0.1700
Data Index: 2149252 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.8423. Min Act: -0.1700
Data Index: 3363396 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.8423. Min Act: -0.1700
Data Index: 7094005 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.8110. Min Act: -0.1700
Data Index: 2378183 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.7798. Min Act: -0.1700
Data Index: 3244078 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.7173. Min Act: -0.1700
Data Index: 3523026 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.7173. Min Act: -0.1700
Data Index: 5746242 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.6235. Min Act: -0.1700
Data Index: 7422775 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.6235. Min Act: -0.1700
Data Index: 6150212 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.6235. Min Act: -0.1700
Data Index: 2341785 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.5923. Min Act: -0.1700
Data Index: 6087557 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.6235. Min Act: -0.1700
Data Index: 6637886 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.5298. Min Act: -0.1700
Data Index: 6785947 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.5298. Min Act: -0.1700
Data Index: 2062400 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.4985. Min Act: -0.1700
Data Index: 7301175 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.4985. Min Act: -0.1700
Data Index: 4209272 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.4985. Min Act: -0.1700
Data Index: 5562624 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1442320 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2485. Min Range: -7.2485
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1543616 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19