Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 403 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.6931. Min Act: -0.1700
Data Index: 5187046 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.5993. Min Act: -0.1700
Data Index: 481653 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.5681. Min Act: -0.1700
Data Index: 8689738 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.5681. Min Act: -0.1700
Data Index: 2405388 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.5368. Min Act: -0.1700
Data Index: 742429 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.4431. Min Act: -0.1700
Data Index: 2877538 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.3806. Min Act: -0.1700
Data Index: 7920555 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.3493. Min Act: -0.1700
Data Index: 1228867 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.3493. Min Act: -0.1700
Data Index: 4343830 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.3181. Min Act: -0.1700
Data Index: 7579812 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.3181. Min Act: -0.1700
Data Index: 3222113 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2868. Min Act: -0.1700
Data Index: 7675624 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.3181. Min Act: -0.1700
Data Index: 4680256 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2556. Min Act: -0.1700
Data Index: 5198768 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2556. Min Act: -0.1700
Data Index: 7881904 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2556. Min Act: -0.1700
Data Index: 8446832 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2556. Min Act: -0.1700
Data Index: 1548262 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2243. Min Act: -0.1700
Data Index: 4984597 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2243. Min Act: -0.1700
Data Index: 1288542 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6931. Min Range: -6.6931
Max Act: 6.2556. Min Act: -0.1700
Data Index: 2234361 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19