Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.7584. Min Act: -0.1700
Data Index: 4663889 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.6959. Min Act: -0.1700
Data Index: 5113473 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.6959. Min Act: -0.1700
Data Index: 650687 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.6959. Min Act: -0.1700
Data Index: 4642017 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.6959. Min Act: -0.1700
Data Index: 7857365 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.6334. Min Act: -0.1700
Data Index: 7603241 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.6334. Min Act: -0.1700
Data Index: 4345596 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.5709. Min Act: -0.1700
Data Index: 3672913 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.5709. Min Act: -0.1700
Data Index: 1774963 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.5084. Min Act: -0.1700
Data Index: 7923350 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.5084. Min Act: -0.1700
Data Index: 6642094 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.4459. Min Act: -0.1700
Data Index: 1460551 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3834. Min Act: -0.1700
Data Index: 7864673 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3834. Min Act: -0.1700
Data Index: 6413263 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3834. Min Act: -0.1700
Data Index: 4102230 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3834. Min Act: -0.1700
Data Index: 6282509 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3834. Min Act: -0.1700
Data Index: 8179565 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3209. Min Act: -0.1700
Data Index: 381914 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.3834. Min Act: -0.1700
Data Index: 7400084 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7584. Min Range: -8.7584
Max Act: 8.2584. Min Act: -0.1700
Data Index: 3744312 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19