Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.9033. Min Act: -0.0000

Data Index: 662651 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7281. Min Act: -0.0000

Data Index: 787054 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6702. Min Act: -0.0000

Data Index: 678024 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.4558. Min Act: -0.0000

Data Index: 628116 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.3583. Min Act: -0.0000

Data Index: 445770 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.3969. Min Act: -0.0000

Data Index: 301270 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.1654. Min Act: -0.0000

Data Index: 950115 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.9177. Min Act: -0.0000

Data Index: 986392 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.2973. Min Act: -0.0000

Data Index: 1210309 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.7565. Min Act: -0.0000

Data Index: 28631 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.8713. Min Act: -0.0000

Data Index: 1320524 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.8601. Min Act: -0.0000

Data Index: 759322 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.9949. Min Act: -0.0000

Data Index: 126059 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.9417. Min Act: -0.0000

Data Index: 405534 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.7947. Min Act: -0.0000

Data Index: 1180706 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.8914. Min Act: -0.0000

Data Index: 72972 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.8849. Min Act: -0.0000

Data Index: 430171 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.7582. Min Act: -0.0000

Data Index: 228664 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.7173. Min Act: -0.0000

Data Index: 932880 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 3.9033. Min Range: -3.9033

Max Act: 2.5720. Min Act: -0.0000

Data Index: 555747 (C4 (Web Text))

Max Activating Token Index: 467