Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.8024. Min Act: -0.1700
Data Index: 2074323 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.6774. Min Act: -0.1700
Data Index: 7866876 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.6774. Min Act: -0.1700
Data Index: 2670506 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.6774. Min Act: -0.1700
Data Index: 5990411 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.6462. Min Act: -0.1700
Data Index: 6763923 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.6149. Min Act: -0.1700
Data Index: 2022241 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5837. Min Act: -0.1700
Data Index: 827908 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5837. Min Act: -0.1700
Data Index: 8292983 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5837. Min Act: -0.1700
Data Index: 717103 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5837. Min Act: -0.1700
Data Index: 3196488 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5212. Min Act: -0.1700
Data Index: 1953412 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5524. Min Act: -0.1700
Data Index: 3126582 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5212. Min Act: -0.1700
Data Index: 5465489 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.5212. Min Act: -0.1700
Data Index: 6726930 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.4587. Min Act: -0.1700
Data Index: 8258071 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.4899. Min Act: -0.1700
Data Index: 4310376 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.4899. Min Act: -0.1700
Data Index: 1637334 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.4899. Min Act: -0.1700
Data Index: 2118994 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.3962. Min Act: -0.1700
Data Index: 6633150 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8024. Min Range: -6.8024
Max Act: 6.3649. Min Act: -0.1700
Data Index: 7674495 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19