Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.8577. Min Act: -0.1700
Data Index: 7176383 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.8265. Min Act: -0.1700
Data Index: 4327299 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.7952. Min Act: -0.1700
Data Index: 3055967 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.6701. Min Act: -0.1700
Data Index: 3013902 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.7326. Min Act: -0.1700
Data Index: 2886442 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.7326. Min Act: -0.1700
Data Index: 1348944 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.6701. Min Act: -0.1700
Data Index: 1502938 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.6231. Min Act: -0.1700
Data Index: 7385214 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.6388. Min Act: -0.1700
Data Index: 1739807 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.6231. Min Act: -0.1700
Data Index: 6475078 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.6231. Min Act: -0.1700
Data Index: 1759309 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5918. Min Act: -0.1700
Data Index: 8673937 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5918. Min Act: -0.1700
Data Index: 892137 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5762. Min Act: -0.1700
Data Index: 5733356 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5762. Min Act: -0.1700
Data Index: 4067810 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5605. Min Act: -0.1700
Data Index: 1595882 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5449. Min Act: -0.1700
Data Index: 1420772 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5605. Min Act: -0.1700
Data Index: 3324455 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5605. Min Act: -0.1700
Data Index: 1437020 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8577. Min Range: -3.8577
Max Act: 3.5292. Min Act: -0.1700
Data Index: 2435504 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19