Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2917. Min Range: -8.2917
Max Act: 8.2917. Min Act: -0.1700
Data Index: 1914942 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.9479. Min Act: -0.1700
Data Index: 5854135 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.7604. Min Act: -0.1700
Data Index: 8157393 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.6354. Min Act: -0.1700
Data Index: 4019079 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.5417. Min Act: -0.1700
Data Index: 8609808 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.4792. Min Act: -0.1700
Data Index: 7170022 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.4792. Min Act: -0.1700
Data Index: 4224851 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.3854. Min Act: -0.1700
Data Index: 2811613 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.2917. Min Act: -0.1700
Data Index: 8335750 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.2604. Min Act: -0.1699
Data Index: 2241405 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.2292. Min Act: -0.1700
Data Index: 278531 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 2916423 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1667. Min Act: -0.1700
Data Index: 2754755 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 4973009 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 3118427 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 6117306 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 6936759 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 671656 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1667. Min Act: -0.1700
Data Index: 4907115 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2917. Min Range: -8.2917
Max Act: 7.1979. Min Act: -0.1700
Data Index: 4117973 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19