Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.5816. Min Act: -0.1700
Data Index: 5521382 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.4566. Min Act: -0.1700
Data Index: 4116004 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.3629. Min Act: -0.1700
Data Index: 4710600 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.3629. Min Act: -0.1700
Data Index: 7746043 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.3316. Min Act: -0.1700
Data Index: 6384317 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2691. Min Act: -0.1700
Data Index: 5542920 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2691. Min Act: -0.1700
Data Index: 7975378 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2379. Min Act: -0.1700
Data Index: 4309150 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2691. Min Act: -0.1700
Data Index: 7329822 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2379. Min Act: -0.1700
Data Index: 5223521 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7841945 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2066. Min Act: -0.1700
Data Index: 7047638 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.1754. Min Act: -0.1700
Data Index: 3507892 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2379. Min Act: -0.1700
Data Index: 6853493 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.2066. Min Act: -0.1700
Data Index: 5809815 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.1754. Min Act: -0.1700
Data Index: 8640475 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.1754. Min Act: -0.1700
Data Index: 7712359 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.1754. Min Act: -0.1700
Data Index: 94609 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.1754. Min Act: -0.1700
Data Index: 8347793 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5816. Min Range: -5.5816
Max Act: 5.1441. Min Act: -0.1700
Data Index: 3264599 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19