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

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

Neuron 3059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3761. Min Act: -0.0002

Data Index: 1076230 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3393. Min Act: -0.0002

Data Index: 827256 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3514. Min Act: -0.0002

Data Index: 1094935 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3480. Min Act: -0.0002

Data Index: 816835 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3477. Min Act: -0.0002

Data Index: 53746 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3478. Min Act: -0.0002

Data Index: 35978 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3209. Min Act: -0.0002

Data Index: 551675 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3249. Min Act: -0.0002

Data Index: 658594 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3439. Min Act: -0.0002

Data Index: 1159131 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3880. Min Act: -0.0002

Data Index: 19622 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3395. Min Act: -0.0002

Data Index: 566963 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3361. Min Act: -0.0002

Data Index: 660330 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3240. Min Act: -0.0002

Data Index: 1050101 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3220. Min Act: -0.0002

Data Index: 76261 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3193. Min Act: -0.0002

Data Index: 874169 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3292. Min Act: -0.0002

Data Index: 267676 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3302. Min Act: -0.0002

Data Index: 296320 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3264. Min Act: -0.0002

Data Index: 852806 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3273. Min Act: -0.0002

Data Index: 486648 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3185. Min Act: -0.0002

Data Index: 851904 (C4 (Web Text))

Max Activating Token Index: 282