Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.4600. Min Act: -0.1700
Data Index: 2943310 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.2412. Min Act: -0.1700
Data Index: 3406810 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.2412. Min Act: -0.1700
Data Index: 1725019 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.0537. Min Act: -0.1700
Data Index: 6129961 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.0537. Min Act: -0.1700
Data Index: 5635330 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.0537. Min Act: -0.1700
Data Index: 4015489 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4600. Min Range: -7.4600
Max Act: 7.0225. Min Act: -0.1700
Data Index: 5400679 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.9287. Min Act: -0.1700
Data Index: 6242188 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.8662. Min Act: -0.1700
Data Index: 2828156 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.8975. Min Act: -0.1700
Data Index: 4684093 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.8037. Min Act: -0.1700
Data Index: 7530659 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.8662. Min Act: -0.1700
Data Index: 1442366 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.7725. Min Act: -0.1700
Data Index: 5120157 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.8037. Min Act: -0.1700
Data Index: 6343464 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.7725. Min Act: -0.1700
Data Index: 6872693 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.7725. Min Act: -0.1700
Data Index: 6871670 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.7412. Min Act: -0.1700
Data Index: 3111458 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.7100. Min Act: -0.1700
Data Index: 4706770 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.6787. Min Act: -0.1700
Data Index: 5957801 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4600. Min Range: -7.4600
Max Act: 6.7100. Min Act: -0.1700
Data Index: 5859356 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19