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

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

Neuron 4995 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.6239. Min Act: -0.0000

Data Index: 127998 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.3732. Min Act: -0.0000

Data Index: 303655 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.2966. Min Act: -0.0000

Data Index: 359174 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0866. Min Act: -0.0000

Data Index: 470335 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.2166. Min Act: -0.0000

Data Index: 965666 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1024679 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0250. Min Act: -0.0000

Data Index: 916331 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0868. Min Act: -0.0000

Data Index: 797694 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1098861 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0590. Min Act: -0.0000

Data Index: 697340 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.2030. Min Act: -0.0000

Data Index: 421118 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0084. Min Act: -0.0000

Data Index: 850219 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.9712. Min Act: -0.0000

Data Index: 910074 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.6239. Min Range: -1.6239

Max Act: 1.0061. Min Act: -0.0000

Data Index: 385477 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1238018 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1254350 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.9337. Min Act: -0.0000

Data Index: 944814 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.9897. Min Act: -0.0000

Data Index: 547261 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.8330. Min Act: -0.0000

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 1.6239. Min Range: -1.6239

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1014390 (C4 (Web Text))

Max Activating Token Index: 371