Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.5766. Min Act: -0.1700
Data Index: 6294048 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.4204. Min Act: -0.1700
Data Index: 4413332 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.4204. Min Act: -0.1700
Data Index: 952072 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.2016. Min Act: -0.1700
Data Index: 4311549 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.2016. Min Act: -0.1700
Data Index: 428104 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.1704. Min Act: -0.1700
Data Index: 2756098 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.1704. Min Act: -0.1700
Data Index: 8031366 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.1704. Min Act: -0.1700
Data Index: 6417918 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.1079. Min Act: -0.1699
Data Index: 3423112 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0766. Min Act: -0.1700
Data Index: 5079777 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0454. Min Act: -0.1700
Data Index: 6086641 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0454. Min Act: -0.1700
Data Index: 7885010 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0141. Min Act: -0.1700
Data Index: 5825496 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0454. Min Act: -0.1700
Data Index: 8096194 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0766. Min Act: -0.1700
Data Index: 7466446 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0766. Min Act: -0.1700
Data Index: 1530063 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0141. Min Act: -0.1700
Data Index: 4736435 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0141. Min Act: -0.1700
Data Index: 2123155 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5766. Min Range: -6.5766
Max Act: 6.0141. Min Act: -0.1700
Data Index: 4476641 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5766. Min Range: -6.5766
Max Act: 5.9516. Min Act: -0.1700
Data Index: 1088567 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19