Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2051 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2709. Min Range: -7.2709
Max Act: 7.2709. Min Act: -0.1700
Data Index: 6076751 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2709. Min Range: -7.2709
Max Act: 7.2084. Min Act: -0.1700
Data Index: 2133939 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2709. Min Range: -7.2709
Max Act: 7.1147. Min Act: -0.1700
Data Index: 4053657 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2709. Min Range: -7.2709
Max Act: 7.1147. Min Act: -0.1700
Data Index: 7043227 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2709. Min Range: -7.2709
Max Act: 7.0834. Min Act: -0.1700
Data Index: 3911621 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.9897. Min Act: -0.1700
Data Index: 1058755 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.9584. Min Act: -0.1700
Data Index: 7894794 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.9584. Min Act: -0.1700
Data Index: 5585451 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8959. Min Act: -0.1700
Data Index: 442079 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.9272. Min Act: -0.1700
Data Index: 5711115 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.9272. Min Act: -0.1700
Data Index: 2962386 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.9272. Min Act: -0.1700
Data Index: 7149788 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8959. Min Act: -0.1700
Data Index: 6749588 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8959. Min Act: -0.1700
Data Index: 5842375 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8334. Min Act: -0.1700
Data Index: 8230605 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8647. Min Act: -0.1700
Data Index: 3580686 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8647. Min Act: -0.1700
Data Index: 2923209 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3320028 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8334. Min Act: -0.1700
Data Index: 5173799 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2709. Min Range: -7.2709
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3366225 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19