Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3183 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0001

Data Index: 1303239 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2768. Min Act: -0.0002

Data Index: 476307 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2727. Min Act: -0.0002

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2606. Min Act: -0.0001

Data Index: 901494 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2549. Min Act: -0.0002

Data Index: 115356 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2699. Min Act: -0.0001

Data Index: 999017 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2619. Min Act: -0.0002

Data Index: 429801 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2491. Min Act: -0.0002

Data Index: 1111553 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2498. Min Act: -0.0001

Data Index: 651443 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2480. Min Act: -0.0002

Data Index: 1277598 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1252251 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2326. Min Act: -0.0002

Data Index: 319277 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2498. Min Act: -0.0001

Data Index: 580696 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2368. Min Act: -0.0002

Data Index: 536517 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2429. Min Act: -0.0001

Data Index: 675921 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2505. Min Act: -0.0002

Data Index: 324519 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2259. Min Act: -0.0001

Data Index: 856935 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2320. Min Act: -0.0002

Data Index: 1030580 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2475. Min Act: -0.0002

Data Index: 1068868 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2452. Min Act: -0.0002

Data Index: 1291459 (C4 (Web Text))

Max Activating Token Index: 60