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

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

Neuron 3130 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.6143. Min Act: -0.0001

Data Index: 821403 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.4411. Min Act: -0.0001

Data Index: 1427207 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.3476. Min Act: -0.0001

Data Index: 1479202 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.5464. Min Act: -0.0001

Data Index: 997749 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.6190. Min Act: -0.0001

Data Index: 1159587 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.6031. Min Act: -0.0001

Data Index: 1382390 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.4431. Min Act: -0.0001

Data Index: 1570097 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.4209. Min Act: -0.0001

Data Index: 806739 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2493. Min Act: -0.0001

Data Index: 1440513 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.4286. Min Act: -0.0001

Data Index: 1415131 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.4560. Min Act: -0.0001

Data Index: 1116349 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.3583. Min Act: -0.0001

Data Index: 86449 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.3755. Min Act: -0.0001

Data Index: 1281384 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2269. Min Act: -0.0001

Data Index: 1263404 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2148. Min Act: -0.0001

Data Index: 1353047 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2840. Min Act: -0.0001

Data Index: 1433287 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2783. Min Act: -0.0001

Data Index: 1626305 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2431. Min Act: -0.0001

Data Index: 1640156 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.3237. Min Act: -0.0001

Data Index: 1448444 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 1.6190. Min Range: -1.6190

Max Act: 1.2706. Min Act: -0.0001

Data Index: 1372050 (Python Code)

Max Activating Token Index: 389