Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2288 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3766. Min Act: -0.1700
Data Index: 6691933 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3610. Min Act: -0.1700
Data Index: 5694776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3766. Min Act: -0.1698
Data Index: 3267782 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3453. Min Act: -0.1695
Data Index: 1911773 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1700
Data Index: 6929003 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1700
Data Index: 3662978 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3453. Min Act: -0.1695
Data Index: 6357478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3453. Min Act: -0.1700
Data Index: 6199197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3610. Min Act: -0.1700
Data Index: 6120296 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3453. Min Act: -0.1697
Data Index: 5603423 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1697
Data Index: 5617582 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3139. Min Act: -0.1689
Data Index: 3300679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1690
Data Index: 5602309 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1697
Data Index: 3442756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1700
Data Index: 2149461 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1698
Data Index: 3671252 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1631
Data Index: 6523412 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3453. Min Act: -0.1698
Data Index: 2075015 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3139. Min Act: -0.1700
Data Index: 6796223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3766. Min Range: -3.3766
Max Act: 3.3296. Min Act: -0.1698
Data Index: 1744280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19