Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.5437. Min Act: -0.1700
Data Index: 5653730 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.3562. Min Act: -0.1700
Data Index: 5619065 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2937. Min Act: -0.1700
Data Index: 8220256 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2937. Min Act: -0.1700
Data Index: 2627240 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2625. Min Act: -0.1700
Data Index: 3592155 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2625. Min Act: -0.1700
Data Index: 6283922 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2000. Min Act: -0.1700
Data Index: 2945137 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2000. Min Act: -0.1700
Data Index: 4889663 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2000. Min Act: -0.1700
Data Index: 2120687 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2000. Min Act: -0.1700
Data Index: 6950272 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1687. Min Act: -0.1700
Data Index: 4185801 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1687. Min Act: -0.1700
Data Index: 5529418 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1687. Min Act: -0.1700
Data Index: 6032372 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.2000. Min Act: -0.1700
Data Index: 8180289 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1687. Min Act: -0.1700
Data Index: 7713831 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3790834 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2250569 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1375. Min Act: -0.1700
Data Index: 1014596 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1375. Min Act: -0.1700
Data Index: 1962814 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5437. Min Range: -5.5437
Max Act: 5.1375. Min Act: -0.1700
Data Index: 5235247 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19