Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6003. Min Range: -8.6003
Max Act: 8.6003. Min Act: -0.1700
Data Index: 3815798 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6003. Min Range: -8.6003
Max Act: 8.2253. Min Act: -0.1700
Data Index: 718984 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.8503. Min Act: -0.1700
Data Index: 7867824 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.7878. Min Act: -0.1700
Data Index: 7913635 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.7565. Min Act: -0.1700
Data Index: 2096014 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.6940. Min Act: -0.1700
Data Index: 6743657 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.6940. Min Act: -0.1700
Data Index: 4371347 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.6315. Min Act: -0.1699
Data Index: 5079860 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.6003. Min Act: -0.1700
Data Index: 1963688 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.6003. Min Act: -0.1700
Data Index: 6813737 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.5690. Min Act: -0.1700
Data Index: 5672436 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.5378. Min Act: -0.1700
Data Index: 4156111 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.5378. Min Act: -0.1700
Data Index: 848437 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.5378. Min Act: -0.1700
Data Index: 4173388 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.5378. Min Act: -0.1700
Data Index: 7390154 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.4753. Min Act: -0.1700
Data Index: 3636921 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.4753. Min Act: -0.1700
Data Index: 5646855 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.5065. Min Act: -0.1700
Data Index: 2180862 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.4440. Min Act: -0.1700
Data Index: 381558 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6003. Min Range: -8.6003
Max Act: 7.4440. Min Act: -0.1700
Data Index: 5675848 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19