Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2540. Min Range: -8.2540
Max Act: 8.2540. Min Act: -0.1700
Data Index: 4817316 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2540. Min Range: -8.2540
Max Act: 8.1915. Min Act: -0.1700
Data Index: 4443982 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.7540. Min Act: -0.1700
Data Index: 5800388 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.6602. Min Act: -0.1700
Data Index: 850186 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.6290. Min Act: -0.1700
Data Index: 6955171 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.6602. Min Act: -0.1700
Data Index: 4533286 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5977. Min Act: -0.1700
Data Index: 2203908 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5665. Min Act: -0.1700
Data Index: 5347525 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5665. Min Act: -0.1700
Data Index: 7455181 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5040. Min Act: -0.1700
Data Index: 4077881 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5352. Min Act: -0.1700
Data Index: 2100756 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5040. Min Act: -0.1700
Data Index: 4166300 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.5040. Min Act: -0.1700
Data Index: 2720209 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.4727. Min Act: -0.1700
Data Index: 1222271 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.4727. Min Act: -0.1700
Data Index: 1528575 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.4415. Min Act: -0.1700
Data Index: 5504307 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.4727. Min Act: -0.1700
Data Index: 1621724 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.4415. Min Act: -0.1700
Data Index: 1286128 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.4102. Min Act: -0.1700
Data Index: 7729507 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2540. Min Range: -8.2540
Max Act: 7.3790. Min Act: -0.1700
Data Index: 5653725 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19