Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2873. Min Range: -6.2873
Max Act: 6.2873. Min Act: -0.1700
Data Index: 2825827 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2873. Min Range: -6.2873
Max Act: 6.2248. Min Act: -0.1700
Data Index: 4016819 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2873. Min Range: -6.2873
Max Act: 6.1623. Min Act: -0.1700
Data Index: 4353312 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2873. Min Range: -6.2873
Max Act: 6.0060. Min Act: -0.1700
Data Index: 2973288 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.9123. Min Act: -0.1700
Data Index: 3255086 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.9123. Min Act: -0.1700
Data Index: 7065356 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.8810. Min Act: -0.1700
Data Index: 1845757 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.8810. Min Act: -0.1700
Data Index: 7339502 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.8498. Min Act: -0.1700
Data Index: 7378827 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.8498. Min Act: -0.1700
Data Index: 2713135 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.8185. Min Act: -0.1700
Data Index: 1831154 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.8185. Min Act: -0.1700
Data Index: 553328 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7873. Min Act: -0.1700
Data Index: 2644052 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7560. Min Act: -0.1700
Data Index: 4326895 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7560. Min Act: -0.1700
Data Index: 2253835 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1584646 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1704216 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7560. Min Act: -0.1700
Data Index: 2712586 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7248. Min Act: -0.1700
Data Index: 8106434 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2873. Min Range: -6.2873
Max Act: 5.7248. Min Act: -0.1700
Data Index: 5914742 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19