Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2669 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3908. Min Range: -9.3908
Max Act: 9.3908. Min Act: -0.1700
Data Index: 6360194 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.7658. Min Act: -0.1700
Data Index: 7128014 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.5783. Min Act: -0.1700
Data Index: 2682233 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.3908. Min Act: -0.1700
Data Index: 2518361 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.3908. Min Act: -0.1700
Data Index: 4748675 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.3283. Min Act: -0.1700
Data Index: 581922 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.3283. Min Act: -0.1700
Data Index: 5827011 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.3283. Min Act: -0.1700
Data Index: 655871 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.2658. Min Act: -0.1700
Data Index: 3920022 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.1408. Min Act: -0.1700
Data Index: 1371444 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.1408. Min Act: -0.1700
Data Index: 5540509 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.1408. Min Act: -0.1700
Data Index: 4856068 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0783. Min Act: -0.1700
Data Index: 3238337 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0783. Min Act: -0.1700
Data Index: 2328993 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0783. Min Act: -0.1700
Data Index: 3549541 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0158. Min Act: -0.1700
Data Index: 4554874 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0158. Min Act: -0.1700
Data Index: 1632487 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0158. Min Act: -0.1700
Data Index: 3263537 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0158. Min Act: -0.1700
Data Index: 6286014 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3908. Min Range: -9.3908
Max Act: 8.0158. Min Act: -0.1700
Data Index: 822842 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19