Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.8873. Min Act: -0.1697
Data Index: 6922703 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.8248. Min Act: -0.1700
Data Index: 6955648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.8248. Min Act: -0.1700
Data Index: 777094 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.8248. Min Act: -0.1700
Data Index: 1582481 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 5973918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 6912660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1876955 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 2910143 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 577155 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1545508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1698
Data Index: 5279592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1688
Data Index: 11845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 5089067 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1258774 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 4647644 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1696
Data Index: 4633431 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1503147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 4168007 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1107289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8873. Min Range: -6.8873
Max Act: 6.7623. Min Act: -0.1693
Data Index: 2440724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19