Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0545. Min Range: -8.0545
Max Act: 8.0545. Min Act: -0.1700
Data Index: 6366687 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.7420. Min Act: -0.1700
Data Index: 2234970 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.7107. Min Act: -0.1700
Data Index: 3029412 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.5232. Min Act: -0.1700
Data Index: 1782132 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.4295. Min Act: -0.1700
Data Index: 2975182 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.1795. Min Act: -0.1700
Data Index: 439946 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.1795. Min Act: -0.1700
Data Index: 3144818 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.1482. Min Act: -0.1700
Data Index: 8432801 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0545. Min Range: -8.0545
Max Act: 7.0857. Min Act: -0.1700
Data Index: 4285707 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.9607. Min Act: -0.1700
Data Index: 5727425 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.9920. Min Act: -0.1700
Data Index: 1061576 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.9607. Min Act: -0.1700
Data Index: 6366686 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.8670. Min Act: -0.1700
Data Index: 6870771 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.8670. Min Act: -0.1700
Data Index: 7562898 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.8670. Min Act: -0.1700
Data Index: 1641382 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.8670. Min Act: -0.1700
Data Index: 7539745 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.8357. Min Act: -0.1700
Data Index: 7125194 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.8045. Min Act: -0.1700
Data Index: 6695885 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.7420. Min Act: -0.1700
Data Index: 3047288 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0545. Min Range: -8.0545
Max Act: 6.7732. Min Act: -0.1700
Data Index: 4242559 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19