Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.5705. Min Act: -0.1700
Data Index: 3538157 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.2892. Min Act: -0.1700
Data Index: 2451453 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.2892. Min Act: -0.1700
Data Index: 2451452 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.2580. Min Act: -0.1700
Data Index: 3836024 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.2267. Min Act: -0.1700
Data Index: 2821658 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1955. Min Act: -0.1700
Data Index: 7119140 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.2267. Min Act: -0.1700
Data Index: 125088 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1955. Min Act: -0.1700
Data Index: 42676 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1642. Min Act: -0.1700
Data Index: 131065 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1642. Min Act: -0.1700
Data Index: 2345227 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1330. Min Act: -0.1700
Data Index: 5841298 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1330. Min Act: -0.1700
Data Index: 6101761 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1330. Min Act: -0.1700
Data Index: 984788 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1017. Min Act: -0.1700
Data Index: 3424300 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5841315 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5841314 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.0392. Min Act: -0.1700
Data Index: 5841256 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.0080. Min Act: -0.1700
Data Index: 5841300 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.0080. Min Act: -0.1700
Data Index: 5841317 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5705. Min Range: -5.5705
Max Act: 5.0392. Min Act: -0.1700
Data Index: 5841269 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19