Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1217 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.1551. Min Act: -0.1700
Data Index: 7110754 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.0301. Min Act: -0.1700
Data Index: 4096691 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.9051. Min Act: -0.1700
Data Index: 2749718 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5242315 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 3820717 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5982476 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 739029 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 5258517 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 7362872 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 2954282 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 3952499 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 1101267 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 5737814 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 6153998 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 5034074 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6239. Min Act: -0.1700
Data Index: 7907055 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6239. Min Act: -0.1700
Data Index: 2546049 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.6239. Min Act: -0.1700
Data Index: 1347927 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.5926. Min Act: -0.1700
Data Index: 4648800 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.5926. Min Act: -0.1700
Data Index: 3749081 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19