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

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

Neuron 518 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: 11.2505. Min Range: -11.2505

Max Act: 11.2505. Min Act: -0.0000

Data Index: 1130233 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 11.2505. Min Range: -11.2505

Max Act: 6.4819. Min Act: -0.0000

Data Index: 93730 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.2142. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 11.2505. Min Range: -11.2505

Max Act: 1.4900. Min Act: -0.0000

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 11.2505. Min Range: -11.2505

Max Act: 1.3429. Min Act: -0.0000

Data Index: 994338 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 11.2505. Min Range: -11.2505

Max Act: 1.2860. Min Act: -0.0000

Data Index: 31298 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 11.2505. Min Range: -11.2505

Max Act: 1.2650. Min Act: -0.0000

Data Index: 361841 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.8960. Min Act: -0.0000

Data Index: 490401 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.7334. Min Act: -0.0000

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1175269 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.9220. Min Act: -0.0000

Data Index: 676410 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1209609 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 11.2505. Min Range: -11.2505

Max Act: 1.0076. Min Act: -0.0000

Data Index: 125234 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.7377. Min Act: -0.0000

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.7385. Min Act: -0.0000

Data Index: 361798 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.6656. Min Act: -0.0000

Data Index: 255263 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.7821. Min Act: -0.0000

Data Index: 433902 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1017610 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.8445. Min Act: -0.0000

Data Index: 144392 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 11.2505. Min Range: -11.2505

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 192