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

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

Neuron 1775 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5598. Min Range: -1.5598

Max Act: 1.5598. Min Act: -0.0002

Data Index: 695306 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.5598. Min Range: -1.5598

Max Act: 1.3296. Min Act: -0.0002

Data Index: 910137 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.5598. Min Range: -1.5598

Max Act: 1.1778. Min Act: -0.0002

Data Index: 549091 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9514. Min Act: -0.0002

Data Index: 218056 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.5598. Min Range: -1.5598

Max Act: 1.0714. Min Act: -0.0002

Data Index: 147560 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8884. Min Act: -0.0002

Data Index: 479085 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9980. Min Act: -0.0002

Data Index: 765513 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9391. Min Act: -0.0002

Data Index: 757499 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9761. Min Act: -0.0002

Data Index: 979166 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8959. Min Act: -0.0002

Data Index: 883592 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9453. Min Act: -0.0002

Data Index: 102557 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8469. Min Act: -0.0002

Data Index: 1090871 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8406. Min Act: -0.0002

Data Index: 1103071 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8266. Min Act: -0.0002

Data Index: 495289 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9339. Min Act: -0.0002

Data Index: 1232693 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8769. Min Act: -0.0002

Data Index: 932222 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.7967. Min Act: -0.0002

Data Index: 844445 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.9144. Min Act: -0.0002

Data Index: 262580 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.7726. Min Act: -0.0002

Data Index: 588223 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 1.5598. Min Range: -1.5598

Max Act: 0.8705. Min Act: -0.0002

Data Index: 119064 (C4 (Web Text))

Max Activating Token Index: 279