Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4334 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.2550. Min Act: -0.1700
Data Index: 1164127 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.2550. Min Act: -0.1700
Data Index: 5782656 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.2238. Min Act: -0.1700
Data Index: 3638445 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.1300. Min Act: -0.1700
Data Index: 7831726 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.1300. Min Act: -0.1700
Data Index: 6755310 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.1300. Min Act: -0.1700
Data Index: 6298650 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0988. Min Act: -0.1700
Data Index: 1365113 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0988. Min Act: -0.1700
Data Index: 3559970 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0675. Min Act: -0.1700
Data Index: 4472103 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0675. Min Act: -0.1700
Data Index: 5547509 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0675. Min Act: -0.1700
Data Index: 401791 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0675. Min Act: -0.1700
Data Index: 8712289 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0363. Min Act: -0.1700
Data Index: 1304 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0363. Min Act: -0.1700
Data Index: 4437741 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0050. Min Act: -0.1700
Data Index: 4736845 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2550. Min Range: -5.2550
Max Act: 4.9738. Min Act: -0.1700
Data Index: 4424256 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2550. Min Range: -5.2550
Max Act: 5.0050. Min Act: -0.1700
Data Index: 4584453 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2550. Min Range: -5.2550
Max Act: 4.9738. Min Act: -0.1700
Data Index: 8660744 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2550. Min Range: -5.2550
Max Act: 4.9738. Min Act: -0.1700
Data Index: 4637333 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2550. Min Range: -5.2550
Max Act: 4.9738. Min Act: -0.1700
Data Index: 4000842 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19