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

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

Neuron 2083 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: 0.5193. Min Range: -0.5193

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1507166 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.5193. Min Act: -0.0001

Data Index: 303941 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1382068 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1538608 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4731. Min Act: -0.0001

Data Index: 1512114 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4921. Min Act: -0.0001

Data Index: 1498879 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4583. Min Act: -0.0001

Data Index: 872781 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4430. Min Act: -0.0001

Data Index: 1442724 (Python Code)

Max Activating Token Index: 659

Text #8

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4833. Min Act: -0.0001

Data Index: 1600334 (Python Code)

Max Activating Token Index: 365

Text #9

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1417215 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4570. Min Act: -0.0001

Data Index: 640293 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4591. Min Act: -0.0001

Data Index: 777061 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1487904 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4616. Min Act: -0.0001

Data Index: 1589233 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1522974 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1612520 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4241. Min Act: -0.0001

Data Index: 92074 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4399. Min Act: -0.0001

Data Index: 1325329 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1421646 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1594484 (Python Code)

Max Activating Token Index: 879