Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1359. Min Range: -6.1359
Max Act: 6.1359. Min Act: -0.1700
Data Index: 8156793 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.9796. Min Act: -0.1700
Data Index: 2890784 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1359. Min Range: -6.1359
Max Act: 6.0109. Min Act: -0.1700
Data Index: 7805280 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.8859. Min Act: -0.1700
Data Index: 6668528 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.8234. Min Act: -0.1700
Data Index: 5548328 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.7921. Min Act: -0.1700
Data Index: 6117776 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.7921. Min Act: -0.1700
Data Index: 1135735 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.7609. Min Act: -0.1700
Data Index: 7588424 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.7296. Min Act: -0.1700
Data Index: 3878805 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6984. Min Act: -0.1700
Data Index: 5115201 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6671. Min Act: -0.1700
Data Index: 1039035 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6046. Min Act: -0.1700
Data Index: 3841704 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6359. Min Act: -0.1700
Data Index: 8552285 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6445100 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6046. Min Act: -0.1700
Data Index: 6899182 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.5734. Min Act: -0.1700
Data Index: 6889824 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.5734. Min Act: -0.1700
Data Index: 7383527 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.6359. Min Act: -0.1700
Data Index: 2446542 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.5734. Min Act: -0.1700
Data Index: 1305198 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1359. Min Range: -6.1359
Max Act: 5.5421. Min Act: -0.1700
Data Index: 3272311 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19