Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.8699. Min Act: -0.1700
Data Index: 5606358 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.6824. Min Act: -0.1700
Data Index: 8294123 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.6199. Min Act: -0.1700
Data Index: 4298254 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.6199. Min Act: -0.1700
Data Index: 3809980 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.6199. Min Act: -0.1700
Data Index: 3110149 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.4949. Min Act: -0.1700
Data Index: 668649 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.4324. Min Act: -0.1700
Data Index: 644659 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.4324. Min Act: -0.1700
Data Index: 2782672 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.3699. Min Act: -0.1700
Data Index: 8673871 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.3074. Min Act: -0.1700
Data Index: 7631273 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.3074. Min Act: -0.1700
Data Index: 3432917 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.3699. Min Act: -0.1700
Data Index: 4555257 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.2449. Min Act: -0.1700
Data Index: 4654773 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.2449. Min Act: -0.1700
Data Index: 870845 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.1824. Min Act: -0.1700
Data Index: 8001847 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.2449. Min Act: -0.1700
Data Index: 7638037 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.1824. Min Act: -0.1700
Data Index: 7241399 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.1824. Min Act: -0.1700
Data Index: 777618 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.1824. Min Act: -0.1700
Data Index: 4853360 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8699. Min Range: -8.8699
Max Act: 8.1824. Min Act: -0.1700
Data Index: 3776892 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19