Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1400 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.3223. Min Act: -0.0000

Data Index: 868090 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2967. Min Act: -0.0000

Data Index: 378542 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2835. Min Act: -0.0000

Data Index: 880228 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1124908 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2655. Min Act: -0.0000

Data Index: 455924 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2564. Min Act: -0.0000

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2681. Min Act: -0.0000

Data Index: 424552 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2437. Min Act: -0.0000

Data Index: 336220 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2609. Min Act: -0.0000

Data Index: 872232 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1042143 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1106843 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2582. Min Act: -0.0000

Data Index: 16840 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2406. Min Act: -0.0000

Data Index: 964831 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2555. Min Act: -0.0000

Data Index: 795373 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2461. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2237. Min Act: -0.0000

Data Index: 369765 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2243. Min Act: -0.0000

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2368. Min Act: -0.0000

Data Index: 737069 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2429. Min Act: -0.0000

Data Index: 632987 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1283604 (C4 (Web Text))

Max Activating Token Index: 553