Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 83 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.4238. Min Act: -0.1700
Data Index: 8532950 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3613. Min Act: -0.1700
Data Index: 2573278 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3926. Min Act: -0.1700
Data Index: 7467930 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3613. Min Act: -0.1700
Data Index: 5134386 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.3301. Min Act: -0.1700
Data Index: 5134385 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2988. Min Act: -0.1700
Data Index: 4385425 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2988. Min Act: -0.1700
Data Index: 4179652 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2988. Min Act: -0.1700
Data Index: 3811606 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2676. Min Act: -0.1700
Data Index: 4179651 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2363. Min Act: -0.1700
Data Index: 6551968 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2676. Min Act: -0.1700
Data Index: 2082221 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2363. Min Act: -0.1700
Data Index: 6126132 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2676. Min Act: -0.1700
Data Index: 4463761 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.2051. Min Act: -0.1700
Data Index: 321326 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 4298849 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 6363256 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1113. Min Act: -0.1700
Data Index: 3287640 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0801. Min Act: -0.1700
Data Index: 4298836 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.1426. Min Act: -0.1700
Data Index: 7528015 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4238. Min Range: -5.4238
Max Act: 5.0801. Min Act: -0.1700
Data Index: 5128110 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19