Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 902 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8585. Min Act: -0.0002

Data Index: 193307 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8585. Min Act: -0.0002

Data Index: 619662 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8447. Min Act: -0.0002

Data Index: 622451 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7671. Min Act: -0.0003

Data Index: 23842 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7841. Min Act: -0.0002

Data Index: 1118457 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7598. Min Act: -0.0002

Data Index: 1223088 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7679. Min Act: -0.0002

Data Index: 1271339 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7678. Min Act: -0.0002

Data Index: 695210 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7349. Min Act: -0.0002

Data Index: 227555 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7610. Min Act: -0.0002

Data Index: 748813 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7435. Min Act: -0.0002

Data Index: 408506 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7302. Min Act: -0.0002

Data Index: 489403 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7477. Min Act: -0.0002

Data Index: 1356036 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7333. Min Act: -0.0002

Data Index: 41865 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7369. Min Act: -0.0002

Data Index: 254747 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7281. Min Act: -0.0002

Data Index: 1602304 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7276. Min Act: -0.0002

Data Index: 863924 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7164. Min Act: -0.0002

Data Index: 675620 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7151. Min Act: -0.0002

Data Index: 649042 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7145. Min Act: -0.0002

Data Index: 78140 (C4 (Web Text))

Max Activating Token Index: 259