Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2163 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.1747. Min Act: -0.1700
Data Index: 7821726 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.1122. Min Act: -0.1700
Data Index: 4310872 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1747. Min Range: -5.1747
Max Act: 5.0809. Min Act: -0.1700
Data Index: 916080 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9872. Min Act: -0.1700
Data Index: 3780558 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9559. Min Act: -0.1700
Data Index: 3627701 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 2452122 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 4570534 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.9247. Min Act: -0.1700
Data Index: 400158 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.8622. Min Act: -0.1700
Data Index: 4875119 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.8622. Min Act: -0.1700
Data Index: 5377554 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 8735859 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.8309. Min Act: -0.1700
Data Index: 2596082 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 6856148 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 309855 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 6555314 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 8458719 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7372. Min Act: -0.1700
Data Index: 7055987 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 1136835 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7684. Min Act: -0.1700
Data Index: 7977093 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1747. Min Range: -5.1747
Max Act: 4.7997. Min Act: -0.1700
Data Index: 8172388 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19