Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 117 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.2658. Min Act: -0.1700
Data Index: 4617228 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.2346. Min Act: -0.1700
Data Index: 4295901 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.2346. Min Act: -0.1700
Data Index: 8225579 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.2033. Min Act: -0.1700
Data Index: 7644063 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.1408. Min Act: -0.1700
Data Index: 6629982 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.0783. Min Act: -0.1700
Data Index: 3964128 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.9533. Min Act: -0.1700
Data Index: 1834201 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.9533. Min Act: -0.1700
Data Index: 2835459 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3951360 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6598986 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.9221. Min Act: -0.1700
Data Index: 4605648 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.8908. Min Act: -0.1700
Data Index: 7710347 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.8283. Min Act: -0.1700
Data Index: 5323536 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.8283. Min Act: -0.1700
Data Index: 5188330 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7971. Min Act: -0.1700
Data Index: 700316 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7658. Min Act: -0.1700
Data Index: 6748802 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7346. Min Act: -0.1700
Data Index: 3826446 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7346. Min Act: -0.1700
Data Index: 4617452 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7346. Min Act: -0.1700
Data Index: 3537678 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6408. Min Act: -0.1700
Data Index: 2810984 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19