Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3751 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.8803. Min Act: -0.1700
Data Index: 1764041 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.8490. Min Act: -0.1700
Data Index: 2154010 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.8490. Min Act: -0.1700
Data Index: 3845459 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.8490. Min Act: -0.1700
Data Index: 1294712 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.7865. Min Act: -0.1700
Data Index: 319702 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.7553. Min Act: -0.1700
Data Index: 3611869 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.7553. Min Act: -0.1700
Data Index: 2941614 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5944819 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5487508 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.7240. Min Act: -0.1700
Data Index: 4278116 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6928. Min Act: -0.1700
Data Index: 1178855 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6303. Min Act: -0.1700
Data Index: 4869750 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6303. Min Act: -0.1700
Data Index: 8664624 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6303. Min Act: -0.1700
Data Index: 8205315 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.6303. Min Act: -0.1700
Data Index: 7460030 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.5990. Min Act: -0.1700
Data Index: 6713113 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5313190 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.5678. Min Act: -0.1700
Data Index: 8137981 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.5678. Min Act: -0.1700
Data Index: 1620546 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8803. Min Range: -5.8803
Max Act: 5.5678. Min Act: -0.1700
Data Index: 6565611 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19