Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.6561. Min Act: -0.1700
Data Index: 3683641 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.6248. Min Act: -0.1700
Data Index: 8098955 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.5936. Min Act: -0.1700
Data Index: 5017020 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.5936. Min Act: -0.1700
Data Index: 75947 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.5936. Min Act: -0.1700
Data Index: 5853023 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.5623. Min Act: -0.1700
Data Index: 3882159 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.5311. Min Act: -0.1700
Data Index: 4352524 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4998. Min Act: -0.1700
Data Index: 309124 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4373. Min Act: -0.1700
Data Index: 6545567 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4373. Min Act: -0.1700
Data Index: 6155237 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4373. Min Act: -0.1700
Data Index: 8382224 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4061. Min Act: -0.1700
Data Index: 6784586 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4061. Min Act: -0.1700
Data Index: 2442000 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4061. Min Act: -0.1700
Data Index: 5114482 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.4061. Min Act: -0.1700
Data Index: 8478793 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.3436. Min Act: -0.1700
Data Index: 1247770 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.3436. Min Act: -0.1700
Data Index: 2569192 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.3123. Min Act: -0.1700
Data Index: 7977349 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.3436. Min Act: -0.1700
Data Index: 6784602 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6561. Min Range: -5.6561
Max Act: 5.3123. Min Act: -0.1700
Data Index: 7578068 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19