Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.9136. Min Act: -0.1700
Data Index: 6898977 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.7886. Min Act: -0.1700
Data Index: 409421 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.2886. Min Act: -0.1700
Data Index: 7464533 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.2261. Min Act: -0.1700
Data Index: 5734779 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.1636. Min Act: -0.1700
Data Index: 2656725 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.1636. Min Act: -0.1700
Data Index: 460192 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.2261. Min Act: -0.1700
Data Index: 7516167 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9136. Min Range: -11.9136
Max Act: 11.1636. Min Act: -0.1700
Data Index: 5617834 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.9136. Min Act: -0.1700
Data Index: 873289 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.9136. Min Act: -0.1700
Data Index: 1493347 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.7886. Min Act: -0.1700
Data Index: 2529668 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.8511. Min Act: -0.1700
Data Index: 1278466 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.9136. Min Act: -0.1700
Data Index: 1336976 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.7886. Min Act: -0.1700
Data Index: 1161523 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.8511. Min Act: -0.1700
Data Index: 3487975 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.8511. Min Act: -0.1700
Data Index: 1904396 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.7886. Min Act: -0.1700
Data Index: 3963572 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.7886. Min Act: -0.1700
Data Index: 64860 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.7261. Min Act: -0.1700
Data Index: 4666052 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9136. Min Range: -11.9136
Max Act: 10.7261. Min Act: -0.1700
Data Index: 7030992 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19