Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5433 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.7891. Min Act: -0.1700
Data Index: 7229835 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.7579. Min Act: -0.1700
Data Index: 935755 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.7266. Min Act: -0.1700
Data Index: 5121159 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6954. Min Act: -0.1700
Data Index: 4073262 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.7266. Min Act: -0.1700
Data Index: 5003055 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6954. Min Act: -0.1700
Data Index: 481829 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6954. Min Act: -0.1700
Data Index: 973320 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6641. Min Act: -0.1700
Data Index: 5121165 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6641. Min Act: -0.1700
Data Index: 5731878 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6641. Min Act: -0.1700
Data Index: 7472650 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6641. Min Act: -0.1700
Data Index: 2401772 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6641. Min Act: -0.1700
Data Index: 7319111 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6329. Min Act: -0.1700
Data Index: 4073260 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1331043 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6016. Min Act: -0.1700
Data Index: 5583242 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6329. Min Act: -0.1700
Data Index: 2054639 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.6016. Min Act: -0.1700
Data Index: 5879030 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.5704. Min Act: -0.1700
Data Index: 7426237 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.5704. Min Act: -0.1700
Data Index: 6056276 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7891. Min Range: -5.7891
Max Act: 5.5704. Min Act: -0.1700
Data Index: 1359566 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19