Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0433. Min Range: -4.0433
Max Act: 4.0433. Min Act: -0.1700
Data Index: 4278490 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0433. Min Range: -4.0433
Max Act: 4.0120. Min Act: -0.1700
Data Index: 706574 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.7932. Min Act: -0.1700
Data Index: 5936121 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.7463. Min Act: -0.1700
Data Index: 2535283 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.7463. Min Act: -0.1700
Data Index: 1243172 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.7463. Min Act: -0.1700
Data Index: 5716936 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6993. Min Act: -0.1700
Data Index: 1942936 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6837. Min Act: -0.1700
Data Index: 4924151 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6837. Min Act: -0.1700
Data Index: 6872761 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6524. Min Act: -0.1700
Data Index: 6647773 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6524. Min Act: -0.1700
Data Index: 903668 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6524. Min Act: -0.1700
Data Index: 1531423 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6524. Min Act: -0.1700
Data Index: 4912314 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6524. Min Act: -0.1700
Data Index: 2148215 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6367. Min Act: -0.1700
Data Index: 8827867 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6367. Min Act: -0.1700
Data Index: 7687365 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6054. Min Act: -0.1700
Data Index: 8814232 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6211. Min Act: -0.1700
Data Index: 2571505 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6054. Min Act: -0.1700
Data Index: 1945806 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0433. Min Range: -4.0433
Max Act: 3.6211. Min Act: -0.1700
Data Index: 901535 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19