Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 993 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.2124. Min Act: -0.1700
Data Index: 526653 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2124. Min Range: -4.2124
Max Act: 4.0405. Min Act: -0.1700
Data Index: 7222314 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9155. Min Act: -0.1700
Data Index: 5927465 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.9155. Min Act: -0.1700
Data Index: 7893058 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8686. Min Act: -0.1700
Data Index: 2442570 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8373. Min Act: -0.1700
Data Index: 3823672 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7904. Min Act: -0.1700
Data Index: 7550486 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.8060. Min Act: -0.1700
Data Index: 7965763 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7591. Min Act: -0.1700
Data Index: 4764994 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7591. Min Act: -0.1700
Data Index: 1530029 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7122. Min Act: -0.1700
Data Index: 2740728 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7435. Min Act: -0.1700
Data Index: 6057184 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7591. Min Act: -0.1700
Data Index: 4542468 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7435. Min Act: -0.1700
Data Index: 6550252 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7435. Min Act: -0.1700
Data Index: 822228 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7278. Min Act: -0.1700
Data Index: 1410029 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7435. Min Act: -0.1700
Data Index: 3408305 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7122. Min Act: -0.1700
Data Index: 7793784 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.7278. Min Act: -0.1700
Data Index: 6389609 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2124. Min Range: -4.2124
Max Act: 3.6965. Min Act: -0.1700
Data Index: 5610927 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19