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

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

Neuron 257 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9584. Min Act: -0.0001

Data Index: 1611546 (Python Code)

Max Activating Token Index: 628

Text #1

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1510760 (Python Code)

Max Activating Token Index: 234

Text #2

Max Range: 1.0448. Min Range: -1.0448

Max Act: 1.0448. Min Act: -0.0001

Data Index: 1543828 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9641. Min Act: -0.0001

Data Index: 1386453 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1513905 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9084. Min Act: -0.0001

Data Index: 1365113 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8766. Min Act: -0.0001

Data Index: 1467563 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1486591 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1157621 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9127. Min Act: -0.0001

Data Index: 1424262 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8764. Min Act: -0.0001

Data Index: 1623336 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9019. Min Act: -0.0001

Data Index: 1372027 (Python Code)

Max Activating Token Index: 568

Text #12

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8592. Min Act: -0.0001

Data Index: 620028 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1389701 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1498948 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8491. Min Act: -0.0001

Data Index: 174076 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1427500 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8403. Min Act: -0.0001

Data Index: 1469290 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8580. Min Act: -0.0001

Data Index: 317351 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1246331 (C4 (Web Text))

Max Activating Token Index: 173