Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 423 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.8229. Min Act: -0.1700
Data Index: 2749135 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.4792. Min Act: -0.1700
Data Index: 5744692 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.3854. Min Act: -0.1700
Data Index: 853946 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.3854. Min Act: -0.1700
Data Index: 45553 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.3542. Min Act: -0.1700
Data Index: 858588 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.3229. Min Act: -0.1700
Data Index: 463756 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.3229. Min Act: -0.1700
Data Index: 6607193 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.2917. Min Act: -0.1700
Data Index: 8709344 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.2604. Min Act: -0.1700
Data Index: 4022949 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.2292. Min Act: -0.1700
Data Index: 7712091 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.2292. Min Act: -0.1700
Data Index: 8265286 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1979. Min Act: -0.1700
Data Index: 8072156 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1667. Min Act: -0.1700
Data Index: 4466663 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1667. Min Act: -0.1700
Data Index: 1042469 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1354. Min Act: -0.1700
Data Index: 2881050 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1667. Min Act: -0.1700
Data Index: 6394397 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1042. Min Act: -0.1700
Data Index: 8355723 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1042. Min Act: -0.1700
Data Index: 7161822 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1147250 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8229. Min Range: -5.8229
Max Act: 5.1354. Min Act: -0.1700
Data Index: 7680735 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19