Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5591 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2041. Min Range: -10.2041
Max Act: 10.2041. Min Act: -0.1700
Data Index: 2320794 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.5791. Min Act: -0.1700
Data Index: 6941972 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.5791. Min Act: -0.1700
Data Index: 2092034 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.5166. Min Act: -0.1700
Data Index: 5854110 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.2041. Min Act: -0.1700
Data Index: 800369 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.0166. Min Act: -0.1700
Data Index: 3928764 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.0166. Min Act: -0.1700
Data Index: 4293405 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2041. Min Range: -10.2041
Max Act: 9.0166. Min Act: -0.1700
Data Index: 2576153 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.9541. Min Act: -0.1700
Data Index: 7280244 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.8916. Min Act: -0.1700
Data Index: 5950086 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.8916. Min Act: -0.1700
Data Index: 4584770 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.8291. Min Act: -0.1700
Data Index: 8017172 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.8291. Min Act: -0.1700
Data Index: 6938696 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.8291. Min Act: -0.1700
Data Index: 1533019 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.7666. Min Act: -0.1700
Data Index: 6564187 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.7666. Min Act: -0.1700
Data Index: 1095823 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.7666. Min Act: -0.1700
Data Index: 3588532 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.7666. Min Act: -0.1700
Data Index: 6364647 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.7666. Min Act: -0.1700
Data Index: 1027241 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2041. Min Range: -10.2041
Max Act: 8.7666. Min Act: -0.1700
Data Index: 7837935 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19