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

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

Neuron 319 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1274190 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3858. Min Act: -0.0000

Data Index: 868956 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3470. Min Act: -0.0000

Data Index: 1345070 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1671. Min Act: -0.0000

Data Index: 58253 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1018980 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3878. Min Act: -0.0000

Data Index: 51442 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3346. Min Act: -0.0000

Data Index: 534464 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2896. Min Act: -0.0001

Data Index: 258977 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2307. Min Act: -0.0000

Data Index: 885051 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1256231 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2812. Min Act: -0.0000

Data Index: 372621 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2772. Min Act: -0.0000

Data Index: 793990 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2119. Min Act: -0.0000

Data Index: 347726 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2404. Min Act: -0.0000

Data Index: 273374 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2153. Min Act: -0.0001

Data Index: 792405 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2840. Min Act: -0.0001

Data Index: 571040 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2205. Min Act: -0.0000

Data Index: 398383 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2247. Min Act: -0.0000

Data Index: 423593 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1860. Min Act: -0.0000

Data Index: 596825 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2179. Min Act: -0.0000

Data Index: 909712 (C4 (Web Text))

Max Activating Token Index: 27