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

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

Neuron 549 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.6042. Min Act: -0.0001

Data Index: 542030 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.2985. Min Act: -0.0001

Data Index: 1294362 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1394. Min Act: -0.0001

Data Index: 1313289 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.2399. Min Act: -0.0001

Data Index: 1161032 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.2246. Min Act: -0.0001

Data Index: 414044 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.2136. Min Act: -0.0001

Data Index: 799412 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1736. Min Act: -0.0001

Data Index: 40424 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1721. Min Act: -0.0001

Data Index: 68954 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.2698. Min Act: -0.0001

Data Index: 792622 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.0896. Min Act: -0.0001

Data Index: 552075 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1901. Min Act: -0.0001

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1167. Min Act: -0.0001

Data Index: 485955 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1503. Min Act: -0.0001

Data Index: 1150843 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.6042. Min Range: -1.6042

Max Act: 0.9249. Min Act: -0.0001

Data Index: 752689 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1649. Min Act: -0.0001

Data Index: 370135 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.2427. Min Act: -0.0001

Data Index: 203855 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.0873. Min Act: -0.0001

Data Index: 494337 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.0887. Min Act: -0.0001

Data Index: 466947 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1116. Min Act: -0.0001

Data Index: 966511 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.6042. Min Range: -1.6042

Max Act: 1.1382. Min Act: -0.0001

Data Index: 840767 (C4 (Web Text))

Max Activating Token Index: 647