Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5104 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.1411. Min Act: -0.1700
Data Index: 8180241 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.1411. Min Act: -0.1700
Data Index: 3771573 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.0161. Min Act: -0.1700
Data Index: 5402623 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.0161. Min Act: -0.1700
Data Index: 6013765 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.0161. Min Act: -0.1700
Data Index: 5253090 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.0161. Min Act: -0.1700
Data Index: 2619521 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9849. Min Act: -0.1700
Data Index: 7057128 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1411. Min Range: -5.1411
Max Act: 5.0161. Min Act: -0.1700
Data Index: 5164427 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9849. Min Act: -0.1700
Data Index: 1643905 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9849. Min Act: -0.1700
Data Index: 4137858 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 3366962 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 4621929 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9224. Min Act: -0.1700
Data Index: 7471257 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 8385739 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 5264009 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 967363 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 3868805 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9224. Min Act: -0.1700
Data Index: 4878241 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9536. Min Act: -0.1700
Data Index: 588860 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1411. Min Range: -5.1411
Max Act: 4.9224. Min Act: -0.1700
Data Index: 7136810 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19