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

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

Neuron 967 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8394. Min Range: -6.8394

Max Act: 6.8394. Min Act: -0.0000

Data Index: 569632 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.8943. Min Act: -0.0000

Data Index: 613891 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.8673. Min Act: -0.0000

Data Index: 1323457 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.4100. Min Act: -0.0000

Data Index: 4800 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.3248. Min Act: -0.0000

Data Index: 522114 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.9238. Min Act: -0.0000

Data Index: 1052441 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.1503. Min Act: -0.0000

Data Index: 1317199 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.2227. Min Act: -0.0000

Data Index: 1283783 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.0775. Min Act: -0.0000

Data Index: 919930 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 6.8394. Min Range: -6.8394

Max Act: 5.0464. Min Act: -0.0000

Data Index: 114245 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.6636. Min Act: -0.0000

Data Index: 10636 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.6372. Min Act: -0.0000

Data Index: 895739 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.8057. Min Act: -0.0000

Data Index: 633387 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.7839. Min Act: -0.0000

Data Index: 274231 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.5741. Min Act: -0.0000

Data Index: 101713 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.3470. Min Act: -0.0000

Data Index: 641536 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.8343. Min Act: -0.0000

Data Index: 863274 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.7681. Min Act: -0.0000

Data Index: 477863 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.4249. Min Act: -0.0000

Data Index: 197781 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 6.8394. Min Range: -6.8394

Max Act: 4.3913. Min Act: -0.0000

Data Index: 1272625 (C4 (Web Text))

Max Activating Token Index: 787