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

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

Neuron 5090 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2835. Min Range: -4.2835

Max Act: 4.2835. Min Act: -0.0000

Data Index: 247467 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.7471. Min Act: -0.0000

Data Index: 1043959 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.5641. Min Act: -0.0000

Data Index: 551734 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.3969. Min Act: -0.0000

Data Index: 295365 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.0529. Min Act: -0.0000

Data Index: 1339732 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.1210. Min Act: -0.0000

Data Index: 506111 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.2077. Min Act: -0.0000

Data Index: 139628 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.2366. Min Act: -0.0000

Data Index: 818675 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.7258. Min Act: -0.0000

Data Index: 738200 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.0286. Min Act: -0.0000

Data Index: 1243599 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 4.2835. Min Range: -4.2835

Max Act: 3.0302. Min Act: -0.0000

Data Index: 1165250 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.9506. Min Act: -0.0000

Data Index: 756814 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.8848. Min Act: -0.0000

Data Index: 526113 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.7252. Min Act: -0.0000

Data Index: 35169 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.8447. Min Act: -0.0000

Data Index: 727222 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.8326. Min Act: -0.0000

Data Index: 1083342 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.7830. Min Act: -0.0000

Data Index: 933033 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.7325. Min Act: -0.0000

Data Index: 1337217 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.5799. Min Act: -0.0000

Data Index: 303267 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 4.2835. Min Range: -4.2835

Max Act: 2.5608. Min Act: -0.0000

Data Index: 1102186 (C4 (Web Text))

Max Activating Token Index: 688