Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.4647. Min Act: -0.1700
Data Index: 1229309 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.2459. Min Act: -0.1700
Data Index: 6016945 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.2459. Min Act: -0.1700
Data Index: 5549081 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.1834. Min Act: -0.1700
Data Index: 4414742 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.1522. Min Act: -0.1700
Data Index: 2774481 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.1209. Min Act: -0.1700
Data Index: 3115813 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.1209. Min Act: -0.1700
Data Index: 664585 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.1209. Min Act: -0.1700
Data Index: 6975993 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.1209. Min Act: -0.1700
Data Index: 8767899 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.0584. Min Act: -0.1700
Data Index: 3662246 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.0584. Min Act: -0.1700
Data Index: 5301232 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4647. Min Range: -6.4647
Max Act: 6.0272. Min Act: -0.1700
Data Index: 7342865 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9647. Min Act: -0.1700
Data Index: 8223332 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9959. Min Act: -0.1700
Data Index: 3115817 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9647. Min Act: -0.1700
Data Index: 1377574 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9647. Min Act: -0.1700
Data Index: 5729969 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4557043 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9022. Min Act: -0.1700
Data Index: 2366876 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.9022. Min Act: -0.1700
Data Index: 835605 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4647. Min Range: -6.4647
Max Act: 5.8709. Min Act: -0.1700
Data Index: 4810065 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19