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

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

Neuron 3864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6992. Min Act: -0.0000

Data Index: 374523 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7347. Min Act: -0.0000

Data Index: 924807 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7305. Min Act: -0.0000

Data Index: 373933 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7532. Min Act: -0.0000

Data Index: 391931 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6939. Min Act: -0.0000

Data Index: 596196 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6890. Min Act: -0.0000

Data Index: 305639 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1039510 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6064. Min Act: -0.0000

Data Index: 846311 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6651. Min Act: -0.0000

Data Index: 283313 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6841. Min Act: -0.0000

Data Index: 954663 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6286. Min Act: -0.0000

Data Index: 40797 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6410. Min Act: -0.0000

Data Index: 214943 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6407. Min Act: -0.0000

Data Index: 798472 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1288256 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1127380 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5750. Min Act: -0.0000

Data Index: 173558 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6107. Min Act: -0.0000

Data Index: 272485 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5876. Min Act: -0.0000

Data Index: 670128 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6038. Min Act: -0.0000

Data Index: 352802 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1056330 (C4 (Web Text))

Max Activating Token Index: 963