Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.7958. Min Act: -0.1700
Data Index: 8281874 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.7333. Min Act: -0.1700
Data Index: 3809360 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.7020. Min Act: -0.1700
Data Index: 4594890 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.6708. Min Act: -0.1700
Data Index: 2882531 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.6083. Min Act: -0.1700
Data Index: 3972942 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.6395. Min Act: -0.1700
Data Index: 1277887 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.6083. Min Act: -0.1700
Data Index: 5004450 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5458. Min Act: -0.1700
Data Index: 6627198 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5458. Min Act: -0.1700
Data Index: 4334453 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5770. Min Act: -0.1700
Data Index: 7109190 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5458. Min Act: -0.1700
Data Index: 537975 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5458. Min Act: -0.1700
Data Index: 2016046 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5770. Min Act: -0.1700
Data Index: 8702487 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5145. Min Act: -0.1700
Data Index: 4727119 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5145. Min Act: -0.1700
Data Index: 4031832 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4833. Min Act: -0.1700
Data Index: 1710782 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4520. Min Act: -0.1700
Data Index: 2319938 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4833. Min Act: -0.1700
Data Index: 1708663 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.4833. Min Act: -0.1700
Data Index: 3399213 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7958. Min Range: -5.7958
Max Act: 5.5145. Min Act: -0.1700
Data Index: 1723028 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19