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

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

Neuron 2632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4319. Min Act: -0.0001

Data Index: 617556 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4106. Min Act: -0.0001

Data Index: 1605667 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3968. Min Act: -0.0001

Data Index: 342426 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4115. Min Act: -0.0001

Data Index: 1370275 (Python Code)

Max Activating Token Index: 935

Text #4

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1240075 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3410. Min Act: -0.0001

Data Index: 1181867 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3580. Min Act: -0.0001

Data Index: 1611439 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3956. Min Act: -0.0001

Data Index: 1459751 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3669. Min Act: -0.0001

Data Index: 344465 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3253. Min Act: -0.0001

Data Index: 809816 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3903. Min Act: -0.0001

Data Index: 84209 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3559. Min Act: -0.0001

Data Index: 1326316 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1323801 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3371. Min Act: -0.0001

Data Index: 1466918 (Python Code)

Max Activating Token Index: 669

Text #14

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3494. Min Act: -0.0001

Data Index: 1626433 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3482. Min Act: -0.0001

Data Index: 1599608 (Python Code)

Max Activating Token Index: 789

Text #16

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3590. Min Act: -0.0001

Data Index: 1479790 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3330. Min Act: -0.0001

Data Index: 1153378 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3229. Min Act: -0.0001

Data Index: 1433827 (Python Code)

Max Activating Token Index: 870

Text #19

Max Range: 0.4319. Min Range: -0.4319

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1232138 (C4 (Web Text))

Max Activating Token Index: 121