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

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

Neuron 1816 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: 0.5158. Min Range: -0.5158

Max Act: 0.4909. Min Act: -0.0001

Data Index: 481025 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4919. Min Act: -0.0001

Data Index: 492071 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.5158. Min Act: -0.0001

Data Index: 142426 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4576. Min Act: -0.0001

Data Index: 101893 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4428. Min Act: -0.0001

Data Index: 640069 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4594. Min Act: -0.0001

Data Index: 481361 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3747. Min Act: -0.0001

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4274. Min Act: -0.0001

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4261. Min Act: -0.0001

Data Index: 729108 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1146286 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4338. Min Act: -0.0000

Data Index: 982477 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4169. Min Act: -0.0001

Data Index: 1345416 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4149. Min Act: -0.0001

Data Index: 938782 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4144. Min Act: -0.0000

Data Index: 828229 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4110. Min Act: -0.0000

Data Index: 904116 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3848. Min Act: -0.0001

Data Index: 1034994 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3948. Min Act: -0.0000

Data Index: 639530 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.3883. Min Act: -0.0001

Data Index: 989104 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4137. Min Act: -0.0001

Data Index: 883267 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.5158. Min Range: -0.5158

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1278890 (C4 (Web Text))

Max Activating Token Index: 716