Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 289 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7673. Min Act: -0.0005

Data Index: 55836 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7712. Min Act: -0.0005

Data Index: 784688 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7319. Min Act: -0.0005

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7312. Min Act: -0.0005

Data Index: 1353286 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6858. Min Act: -0.0005

Data Index: 29765 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7084. Min Act: -0.0005

Data Index: 977390 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6748. Min Act: -0.0005

Data Index: 380258 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7165. Min Act: -0.0005

Data Index: 896167 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6391. Min Act: -0.0005

Data Index: 1096643 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7035. Min Act: -0.0005

Data Index: 625488 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6535. Min Act: -0.0005

Data Index: 716457 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6763. Min Act: -0.0005

Data Index: 404575 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6864. Min Act: -0.0005

Data Index: 946826 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6614. Min Act: -0.0005

Data Index: 1012353 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6655. Min Act: -0.0005

Data Index: 336065 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5945. Min Act: -0.0005

Data Index: 385419 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6330. Min Act: -0.0005

Data Index: 705559 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6355. Min Act: -0.0005

Data Index: 836075 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6338. Min Act: -0.0005

Data Index: 1081454 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6465. Min Act: -0.0005

Data Index: 1002904 (C4 (Web Text))

Max Activating Token Index: 790