Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2889. Min Act: -0.0003

Data Index: 931473 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2674. Min Act: -0.0003

Data Index: 672464 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2469. Min Act: -0.0003

Data Index: 149222 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2733. Min Act: -0.0003

Data Index: 904975 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2689. Min Act: -0.0003

Data Index: 981007 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2562. Min Act: -0.0003

Data Index: 329889 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2563. Min Act: -0.0003

Data Index: 14677 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2456. Min Act: -0.0003

Data Index: 925075 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2578. Min Act: -0.0003

Data Index: 638796 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2376. Min Act: -0.0003

Data Index: 178551 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2643. Min Act: -0.0003

Data Index: 787488 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2385. Min Act: -0.0003

Data Index: 1108734 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2366. Min Act: -0.0003

Data Index: 690669 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2276. Min Act: -0.0003

Data Index: 1118575 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2332. Min Act: -0.0003

Data Index: 1368925 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2248. Min Act: -0.0003

Data Index: 1573175 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2253. Min Act: -0.0003

Data Index: 956685 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2312. Min Act: -0.0003

Data Index: 1544872 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2131. Min Act: -0.0003

Data Index: 846895 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2215. Min Act: -0.0003

Data Index: 1438040 (Python Code)

Max Activating Token Index: 810