Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2164 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.5790. Min Act: -0.1700
Data Index: 2562887 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.1102. Min Act: -0.1700
Data Index: 2252318 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.1415. Min Act: -0.1700
Data Index: 3328397 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.1102. Min Act: -0.1700
Data Index: 6038429 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0477. Min Act: -0.1700
Data Index: 4401060 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0477. Min Act: -0.1700
Data Index: 8239169 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0165. Min Act: -0.1700
Data Index: 4545678 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0165. Min Act: -0.1700
Data Index: 4380549 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0165. Min Act: -0.1700
Data Index: 4121699 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0477. Min Act: -0.1700
Data Index: 5272036 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.9540. Min Act: -0.1700
Data Index: 6882018 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5790. Min Range: -7.5790
Max Act: 7.0165. Min Act: -0.1700
Data Index: 6059538 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.9227. Min Act: -0.1700
Data Index: 155710 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.9227. Min Act: -0.1700
Data Index: 6452434 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.8915. Min Act: -0.1700
Data Index: 8448211 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.8915. Min Act: -0.1700
Data Index: 3904650 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.8915. Min Act: -0.1700
Data Index: 7121386 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.8915. Min Act: -0.1700
Data Index: 4794606 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.8290. Min Act: -0.1700
Data Index: 6170887 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5790. Min Range: -7.5790
Max Act: 6.8602. Min Act: -0.1700
Data Index: 4708923 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19