Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.2709. Min Act: -0.1700
Data Index: 5826949 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.2084. Min Act: -0.1700
Data Index: 3749903 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.1772. Min Act: -0.1700
Data Index: 828890 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.1772. Min Act: -0.1700
Data Index: 8110816 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.1147. Min Act: -0.1700
Data Index: 5330698 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.0522. Min Act: -0.1700
Data Index: 2921987 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2709. Min Range: -8.2709
Max Act: 8.0209. Min Act: -0.1700
Data Index: 7121947 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.9584. Min Act: -0.1700
Data Index: 7052447 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.9584. Min Act: -0.1700
Data Index: 8704251 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.9584. Min Act: -0.1700
Data Index: 5069832 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.9272. Min Act: -0.1700
Data Index: 1960285 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.9272. Min Act: -0.1700
Data Index: 639681 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.9272. Min Act: -0.1700
Data Index: 6919143 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8959. Min Act: -0.1700
Data Index: 532935 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8959. Min Act: -0.1700
Data Index: 1436427 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8959. Min Act: -0.1700
Data Index: 4552837 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8959. Min Act: -0.1700
Data Index: 2625702 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8959. Min Act: -0.1700
Data Index: 5625239 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8959. Min Act: -0.1700
Data Index: 7437102 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2709. Min Range: -8.2709
Max Act: 7.8647. Min Act: -0.1700
Data Index: 2158712 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19