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

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

Neuron 158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1511446 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.5018. Min Act: 0.0000

Data Index: 1408845 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.5316. Min Act: -0.0000

Data Index: 868543 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1259745 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1573798 (Python Code)

Max Activating Token Index: 132

Text #5

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4791. Min Act: 0.0000

Data Index: 1616873 (Python Code)

Max Activating Token Index: 136

Text #6

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1362034 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1579199 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4281. Min Act: -0.0000

Data Index: 935810 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4126. Min Act: -0.0000

Data Index: 482519 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1595732 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4194. Min Act: -0.0000

Data Index: 816187 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1384222 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1477135 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1590495 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1490785 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1472111 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1450481 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1020310 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3619. Min Act: 0.0000

Data Index: 1510231 (Python Code)

Max Activating Token Index: 58