Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.8936. Min Act: -0.1700
Data Index: 279188 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.8936. Min Act: -0.1700
Data Index: 7141693 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.8311. Min Act: -0.1700
Data Index: 7356815 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.5811. Min Act: -0.1700
Data Index: 8255753 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.5811. Min Act: -0.1700
Data Index: 3232273 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.3936. Min Act: -0.1700
Data Index: 122568 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.3936. Min Act: -0.1700
Data Index: 2884527 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.3311. Min Act: -0.1700
Data Index: 5896956 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.2686. Min Act: -0.1700
Data Index: 4490610 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.2061. Min Act: -0.1700
Data Index: 8067820 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.2061. Min Act: -0.1700
Data Index: 2149044 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.2061. Min Act: -0.1700
Data Index: 616084 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.1748. Min Act: -0.1700
Data Index: 656111 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.1436. Min Act: -0.1700
Data Index: 4942679 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.0811. Min Act: -0.1700
Data Index: 1643267 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.0811. Min Act: -0.1700
Data Index: 656109 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8936. Min Range: -8.8936
Max Act: 8.0186. Min Act: -0.1700
Data Index: 7577638 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8936. Min Range: -8.8936
Max Act: 7.9873. Min Act: -0.1700
Data Index: 2200585 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8936. Min Range: -8.8936
Max Act: 7.9561. Min Act: -0.1700
Data Index: 1340740 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8936. Min Range: -8.8936
Max Act: 7.9873. Min Act: -0.1700
Data Index: 2468659 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19