Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 227 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1550. Min Range: -8.1550
Max Act: 8.1550. Min Act: -0.1700
Data Index: 5728090 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.9363. Min Act: -0.1700
Data Index: 278402 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.6550. Min Act: -0.1700
Data Index: 8266745 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.6238. Min Act: -0.1700
Data Index: 473601 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5925. Min Act: -0.1700
Data Index: 5886762 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5925. Min Act: -0.1700
Data Index: 8776709 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5613. Min Act: -0.1700
Data Index: 679777 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5613. Min Act: -0.1700
Data Index: 89747 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5613. Min Act: -0.1700
Data Index: 3923487 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5613. Min Act: -0.1700
Data Index: 4101233 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5300. Min Act: -0.1700
Data Index: 3332905 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.5613. Min Act: -0.1700
Data Index: 151016 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.4363. Min Act: -0.1700
Data Index: 3185465 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.4363. Min Act: -0.1700
Data Index: 752422 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.4363. Min Act: -0.1700
Data Index: 5720706 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.4050. Min Act: -0.1700
Data Index: 1536033 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.3738. Min Act: -0.1700
Data Index: 6940088 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.4050. Min Act: -0.1700
Data Index: 6250641 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.4050. Min Act: -0.1700
Data Index: 4264691 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1550. Min Range: -8.1550
Max Act: 7.3738. Min Act: -0.1700
Data Index: 2259906 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19