Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2582. Min Range: -3.2582
Max Act: 3.2582. Min Act: -0.1700
Data Index: 921930 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2582. Min Range: -3.2582
Max Act: 3.1638. Min Act: -0.1700
Data Index: 4902848 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9904. Min Act: -0.1700
Data Index: 1474903 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9746. Min Act: -0.1700
Data Index: 6445762 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9587. Min Act: -0.1700
Data Index: 3169976 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9429. Min Act: -0.1700
Data Index: 1480278 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9429. Min Act: -0.1680
Data Index: 5903555 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9587. Min Act: -0.1700
Data Index: 5036018 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9429. Min Act: -0.1700
Data Index: 1226113 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9429. Min Act: -0.1700
Data Index: 2240374 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9429. Min Act: -0.1699
Data Index: 832270 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.9112. Min Act: -0.1699
Data Index: 6716314 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8954. Min Act: -0.1700
Data Index: 8311243 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1433362 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8954. Min Act: -0.1698
Data Index: 5894592 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8954. Min Act: -0.1700
Data Index: 881781 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8954. Min Act: -0.1700
Data Index: 2771327 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8636. Min Act: -0.1694
Data Index: 1248052 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8477. Min Act: -0.1700
Data Index: 5071359 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2582. Min Range: -3.2582
Max Act: 2.8477. Min Act: -0.1700
Data Index: 2128528 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19