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

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

Neuron 2066 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: 0.5380. Min Range: -0.5380

Max Act: 0.5380. Min Act: -0.0000

Data Index: 964847 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.5252. Min Act: -0.0000

Data Index: 228305 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4760. Min Act: -0.0000

Data Index: 824201 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4677. Min Act: -0.0000

Data Index: 589517 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4818. Min Act: -0.0000

Data Index: 784076 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1106133 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4610. Min Act: -0.0001

Data Index: 322056 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1129159 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4455. Min Act: -0.0000

Data Index: 762885 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4411. Min Act: 0.0002

Data Index: 786125 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4588. Min Act: -0.0000

Data Index: 784017 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4424. Min Act: -0.0000

Data Index: 293791 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4288. Min Act: -0.0000

Data Index: 656829 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4214. Min Act: -0.0000

Data Index: 603551 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1318649 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1167123 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4092. Min Act: -0.0000

Data Index: 955462 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4227. Min Act: -0.0000

Data Index: 143869 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4375. Min Act: -0.0000

Data Index: 14962 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4229. Min Act: 0.0001

Data Index: 514242 (C4 (Web Text))

Max Activating Token Index: 51