Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2827 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7375. Min Act: -0.0001

Data Index: 1552534 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7369. Min Act: -0.0001

Data Index: 1012819 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7020. Min Act: -0.0001

Data Index: 718902 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6155. Min Act: -0.0001

Data Index: 289228 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7162. Min Act: -0.0001

Data Index: 827036 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7160. Min Act: -0.0001

Data Index: 1248530 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.7465. Min Act: -0.0001

Data Index: 488880 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6949. Min Act: -0.0001

Data Index: 532619 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6427. Min Act: -0.0001

Data Index: 922140 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1273271 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1555495 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6275. Min Act: -0.0001

Data Index: 513003 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6540. Min Act: -0.0001

Data Index: 1160110 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6009. Min Act: -0.0001

Data Index: 113995 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6681. Min Act: -0.0001

Data Index: 580802 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6025. Min Act: -0.0001

Data Index: 85708 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6039. Min Act: -0.0001

Data Index: 21588 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6433. Min Act: -0.0001

Data Index: 893007 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.5877. Min Act: -0.0001

Data Index: 436378 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.7465. Min Range: -0.7465

Max Act: 0.6221. Min Act: -0.0001

Data Index: 683978 (C4 (Web Text))

Max Activating Token Index: 186