Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.7727. Min Act: -0.1700
Data Index: 5418981 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.5852. Min Act: -0.1700
Data Index: 4678788 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.3977. Min Act: -0.1700
Data Index: 7820759 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.3352. Min Act: -0.1700
Data Index: 5873286 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.3352. Min Act: -0.1700
Data Index: 6157393 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.2102. Min Act: -0.1700
Data Index: 4330881 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.2102. Min Act: -0.1700
Data Index: 1732989 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.2102. Min Act: -0.1700
Data Index: 242490 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.2727. Min Act: -0.1700
Data Index: 8109615 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.0852. Min Act: -0.1700
Data Index: 2232249 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.0852. Min Act: -0.1700
Data Index: 8276793 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.0852. Min Act: -0.1697
Data Index: 6383939 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.0227. Min Act: -0.1700
Data Index: 4111487 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7727. Min Range: -9.7727
Max Act: 9.0227. Min Act: -0.1700
Data Index: 3187288 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7727. Min Range: -9.7727
Max Act: 8.9602. Min Act: -0.1700
Data Index: 4890752 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7727. Min Range: -9.7727
Max Act: 8.8977. Min Act: -0.1700
Data Index: 329591 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7727. Min Range: -9.7727
Max Act: 8.9602. Min Act: -0.1700
Data Index: 3135868 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7727. Min Range: -9.7727
Max Act: 8.8977. Min Act: -0.1700
Data Index: 2074176 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7727. Min Range: -9.7727
Max Act: 8.8977. Min Act: -0.1700
Data Index: 7081455 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7727. Min Range: -9.7727
Max Act: 8.8352. Min Act: -0.1700
Data Index: 1885196 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19