Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.1939. Min Act: -0.1700
Data Index: 7351185 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.1627. Min Act: -0.1700
Data Index: 4584816 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.1314. Min Act: -0.1700
Data Index: 182618 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.0377. Min Act: -0.1700
Data Index: 7905098 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.0377. Min Act: -0.1700
Data Index: 801870 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9439. Min Act: -0.1700
Data Index: 4355130 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9127. Min Act: -0.1700
Data Index: 7295215 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9439. Min Act: -0.1700
Data Index: 444892 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7210512 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.8502. Min Act: -0.1700
Data Index: 1675435 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.8189. Min Act: -0.1700
Data Index: 3196865 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.7564. Min Act: -0.1700
Data Index: 1177834 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.7564. Min Act: -0.1700
Data Index: 508151 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.6627. Min Act: -0.1700
Data Index: 7792091 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.7564. Min Act: -0.1700
Data Index: 5633141 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.7252. Min Act: -0.1700
Data Index: 1725351 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.6939. Min Act: -0.1700
Data Index: 981180 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.7252. Min Act: -0.1700
Data Index: 2588914 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.6002. Min Act: -0.1700
Data Index: 1663447 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.6314. Min Act: -0.1700
Data Index: 5651827 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19