Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4238 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0856. Min Range: -6.0856
Max Act: 6.0856. Min Act: -0.1700
Data Index: 3473450 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0856. Min Range: -6.0856
Max Act: 6.0543. Min Act: -0.1700
Data Index: 8635050 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.9606. Min Act: -0.1700
Data Index: 1637031 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.9293. Min Act: -0.1700
Data Index: 239849 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.9293. Min Act: -0.1700
Data Index: 5639587 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.8981. Min Act: -0.1700
Data Index: 2432726 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.8981. Min Act: -0.1700
Data Index: 6486816 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.6481. Min Act: -0.1700
Data Index: 594476 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.6481. Min Act: -0.1700
Data Index: 4852925 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.5856. Min Act: -0.1700
Data Index: 3218295 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.5543. Min Act: -0.1700
Data Index: 6778914 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.5231. Min Act: -0.1700
Data Index: 4007613 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.4918. Min Act: -0.1700
Data Index: 5576096 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.4606. Min Act: -0.1700
Data Index: 5354800 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.4606. Min Act: -0.1700
Data Index: 6768520 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.4606. Min Act: -0.1700
Data Index: 704871 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.4606. Min Act: -0.1700
Data Index: 353777 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.4293. Min Act: -0.1700
Data Index: 6473902 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.3981. Min Act: -0.1700
Data Index: 2709519 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0856. Min Range: -6.0856
Max Act: 5.3981. Min Act: -0.1700
Data Index: 4687743 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19