Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 704 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.2417. Min Act: -0.1700
Data Index: 5137450 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.2104. Min Act: -0.1700
Data Index: 2352214 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.1167. Min Act: -0.1700
Data Index: 5055348 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.0854. Min Act: -0.1700
Data Index: 8249214 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.0854. Min Act: -0.1700
Data Index: 4680090 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2417. Min Range: -7.2417
Max Act: 7.0229. Min Act: -0.1700
Data Index: 2886056 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9604. Min Act: -0.1700
Data Index: 2530544 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9292. Min Act: -0.1700
Data Index: 3932632 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.9292. Min Act: -0.1700
Data Index: 3199272 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 7648711 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 6172879 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 768180 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 14900 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8667. Min Act: -0.1700
Data Index: 6111499 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8354. Min Act: -0.1700
Data Index: 4459287 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8042. Min Act: -0.1700
Data Index: 8066430 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.8042. Min Act: -0.1700
Data Index: 445260 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.7729. Min Act: -0.1700
Data Index: 3264798 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.7417. Min Act: -0.1700
Data Index: 8026095 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2417. Min Range: -7.2417
Max Act: 6.7104. Min Act: -0.1700
Data Index: 7039676 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19