Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.4390. Min Act: -0.1700
Data Index: 2286161 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.2515. Min Act: -0.1700
Data Index: 2599941 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.1578. Min Act: -0.1700
Data Index: 878687 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.1578. Min Act: -0.1700
Data Index: 4113318 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.1265. Min Act: -0.1700
Data Index: 5060999 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.0015. Min Act: -0.1700
Data Index: 4805979 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.0328. Min Act: -0.1700
Data Index: 4246913 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.0015. Min Act: -0.1700
Data Index: 5803255 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4390. Min Range: -7.4390
Max Act: 7.0015. Min Act: -0.1700
Data Index: 2203440 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.9703. Min Act: -0.1700
Data Index: 7265937 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.9703. Min Act: -0.1700
Data Index: 1883265 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.8765. Min Act: -0.1700
Data Index: 3098991 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.8765. Min Act: -0.1700
Data Index: 6647176 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.7828. Min Act: -0.1700
Data Index: 7843771 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.7828. Min Act: -0.1700
Data Index: 8164152 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.8140. Min Act: -0.1700
Data Index: 6985931 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.7828. Min Act: -0.1700
Data Index: 6927458 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.7203. Min Act: -0.1700
Data Index: 2843474 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.7203. Min Act: -0.1700
Data Index: 4381591 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4390. Min Range: -7.4390
Max Act: 6.7515. Min Act: -0.1700
Data Index: 5890232 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19