Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1122 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7611. Min Act: -0.0000

Data Index: 263270 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7721. Min Act: -0.0000

Data Index: 337063 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6990. Min Act: -0.0001

Data Index: 487257 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7358. Min Act: -0.0001

Data Index: 513367 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6799. Min Act: -0.0001

Data Index: 256811 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6914. Min Act: -0.0001

Data Index: 788351 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6597. Min Act: -0.0001

Data Index: 43315 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6533. Min Act: -0.0001

Data Index: 944917 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6563. Min Act: -0.0001

Data Index: 1563576 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6474. Min Act: -0.0001

Data Index: 1260369 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6039. Min Act: -0.0001

Data Index: 894320 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6186. Min Act: -0.0001

Data Index: 842361 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6343. Min Act: -0.0001

Data Index: 836111 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6792. Min Act: -0.0001

Data Index: 383108 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6162. Min Act: -0.0000

Data Index: 112380 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1072676 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6524. Min Act: -0.0001

Data Index: 1528572 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6028. Min Act: -0.0001

Data Index: 460219 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6233. Min Act: -0.0001

Data Index: 868567 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6148. Min Act: -0.0001

Data Index: 379353 (C4 (Web Text))

Max Activating Token Index: 111