Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2173 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.9699. Min Act: -0.1700
Data Index: 8279372 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.7823. Min Act: -0.1700
Data Index: 5507581 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.7510. Min Act: -0.1700
Data Index: 5652623 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.6728. Min Act: -0.1700
Data Index: 4532595 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.6102. Min Act: -0.1700
Data Index: 1427284 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5945. Min Act: -0.1700
Data Index: 497283 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.6102. Min Act: -0.1700
Data Index: 1450806 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5945. Min Act: -0.1700
Data Index: 1592763 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5945. Min Act: -0.1700
Data Index: 3215095 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5789. Min Act: -0.1700
Data Index: 910754 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5632. Min Act: -0.1700
Data Index: 7727529 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5006. Min Act: -0.1700
Data Index: 5048330 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5162. Min Act: -0.1700
Data Index: 1592764 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5319. Min Act: -0.1700
Data Index: 4180984 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5162. Min Act: -0.1700
Data Index: 5885299 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.4849. Min Act: -0.1700
Data Index: 6990910 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.5006. Min Act: -0.1700
Data Index: 903381 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.4536. Min Act: -0.1700
Data Index: 204158 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.4693. Min Act: -0.1700
Data Index: 6938510 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9699. Min Range: -3.9699
Max Act: 3.4693. Min Act: -0.1700
Data Index: 2701103 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19