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

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

Neuron 1681 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4882. Min Act: -0.0000

Data Index: 621007 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4790. Min Act: -0.0000

Data Index: 476021 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3409. Min Act: -0.0000

Data Index: 2560 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1183948 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4314. Min Act: -0.0000

Data Index: 908676 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4194. Min Act: -0.0000

Data Index: 364609 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3487. Min Act: -0.0000

Data Index: 110398 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3128. Min Act: -0.0000

Data Index: 245248 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3812. Min Act: -0.0000

Data Index: 525573 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1305624 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3355. Min Act: -0.0000

Data Index: 579648 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2385. Min Act: -0.0000

Data Index: 946474 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3139. Min Act: -0.0000

Data Index: 593678 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1263154 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4343. Min Act: -0.0000

Data Index: 846041 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1319582 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2488. Min Act: -0.0000

Data Index: 368768 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1101118 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1544. Min Act: -0.0000

Data Index: 531100 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1215. Min Act: -0.0000

Data Index: 945480 (C4 (Web Text))

Max Activating Token Index: 865