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

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

Neuron 4624 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1074119 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.3345. Min Act: 0.0000

Data Index: 258886 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.3010. Min Act: -0.0000

Data Index: 70713 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1185189 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.2916. Min Act: -0.0000

Data Index: 24842 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1295. Min Act: -0.0000

Data Index: 356652 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0942. Min Act: -0.0000

Data Index: 761918 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1163. Min Act: -0.0000

Data Index: 64022 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1117280 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.1712. Min Act: -0.0000

Data Index: 283579 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0864. Min Act: -0.0000

Data Index: 860595 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9939. Min Act: -0.0000

Data Index: 691781 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9817. Min Act: -0.0000

Data Index: 744082 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9874. Min Act: -0.0000

Data Index: 826662 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.8790. Min Act: -0.0000

Data Index: 657150 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9745. Min Act: -0.0000

Data Index: 805279 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9784. Min Act: -0.0000

Data Index: 174640 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.5170. Min Range: -1.5170

Max Act: 1.0524. Min Act: -0.0000

Data Index: 255446 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9569. Min Act: -0.0000

Data Index: 246327 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.5170. Min Range: -1.5170

Max Act: 0.9548. Min Act: 0.0000

Data Index: 725461 (C4 (Web Text))

Max Activating Token Index: 367