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

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

Neuron 89 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.5372. Min Act: -0.0001

Data Index: 592525 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.3685. Min Act: -0.0001

Data Index: 724982 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1378. Min Act: -0.0000

Data Index: 48273 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1225. Min Act: -0.0001

Data Index: 83382 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0779. Min Act: -0.0000

Data Index: 432924 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0841. Min Act: -0.0000

Data Index: 572438 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0305. Min Act: -0.0001

Data Index: 1015684 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0863. Min Act: -0.0000

Data Index: 413137 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9856. Min Act: -0.0001

Data Index: 187338 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0048. Min Act: -0.0001

Data Index: 81182 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9934. Min Act: -0.0001

Data Index: 1174788 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0202. Min Act: -0.0001

Data Index: 191366 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9171. Min Act: -0.0001

Data Index: 1295097 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9936. Min Act: -0.0000

Data Index: 198440 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9900. Min Act: -0.0001

Data Index: 1023751 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1132080 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1101161 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9457. Min Act: -0.0000

Data Index: 976717 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9181. Min Act: -0.0001

Data Index: 58128 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9323. Min Act: -0.0001

Data Index: 722180 (C4 (Web Text))

Max Activating Token Index: 976