Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.8647. Min Act: -0.1699
Data Index: 5976990 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.8647. Min Act: -0.1696
Data Index: 6730944 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7804. Min Act: -0.1693
Data Index: 7774 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7804. Min Act: -0.1700
Data Index: 1342670 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7555. Min Act: -0.1693
Data Index: 5704219 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7638. Min Act: -0.1669
Data Index: 4351174 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7472. Min Act: -0.1688
Data Index: 2755137 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7472. Min Act: -0.1700
Data Index: 8545661 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7225. Min Act: -0.1699
Data Index: 4666962 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7143. Min Act: -0.1700
Data Index: 8635978 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.7143. Min Act: -0.1700
Data Index: 8635990 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6898. Min Act: -0.1647
Data Index: 7079252 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6735. Min Act: -0.1699
Data Index: 4037241 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6816. Min Act: -0.1700
Data Index: 7061037 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6735. Min Act: -0.1700
Data Index: 2212036 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6735. Min Act: -0.1657
Data Index: 2665400 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6898. Min Act: -0.1698
Data Index: 2341209 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6735. Min Act: -0.1657
Data Index: 5190497 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6816. Min Act: -0.1669
Data Index: 8007443 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8647. Min Range: -0.8647
Max Act: 0.6735. Min Act: -0.1697
Data Index: 7338672 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19