Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0988. Min Range: -6.0988
Max Act: 6.0988. Min Act: -0.1700
Data Index: 4240399 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.8176. Min Act: -0.1700
Data Index: 4757142 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.5988. Min Act: -0.1700
Data Index: 7827940 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1614978 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.5051. Min Act: -0.1700
Data Index: 4498946 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.4738. Min Act: -0.1700
Data Index: 4391291 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 7503399 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 7016813 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.4738. Min Act: -0.1700
Data Index: 156939 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3704432 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3801. Min Act: -0.1700
Data Index: 468340 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 6397123 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3488. Min Act: -0.1700
Data Index: 2092564 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3801. Min Act: -0.1700
Data Index: 8548721 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3801. Min Act: -0.1700
Data Index: 5612167 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3488. Min Act: -0.1700
Data Index: 857091 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3488. Min Act: -0.1700
Data Index: 3190186 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3488. Min Act: -0.1700
Data Index: 4469124 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3176. Min Act: -0.1700
Data Index: 6187583 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0988. Min Range: -6.0988
Max Act: 5.3176. Min Act: -0.1700
Data Index: 4409194 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19