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

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

Neuron 4997 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.5006. Min Act: -0.0000

Data Index: 764137 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.5282. Min Act: -0.0000

Data Index: 1168780 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1135140 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.3105. Min Act: -0.0000

Data Index: 389243 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.3500. Min Act: -0.0000

Data Index: 249985 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1156421 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.4066. Min Act: -0.0000

Data Index: 846411 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.3291. Min Act: -0.0000

Data Index: 44109 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2261. Min Act: -0.0000

Data Index: 133842 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.1644. Min Act: -0.0000

Data Index: 64271 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2700. Min Act: -0.0000

Data Index: 916772 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2500. Min Act: -0.0000

Data Index: 967670 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2311. Min Act: -0.0000

Data Index: 440603 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1265038 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2190. Min Act: -0.0000

Data Index: 530752 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2610. Min Act: -0.0000

Data Index: 414511 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2220. Min Act: -0.0000

Data Index: 653774 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2047. Min Act: -0.0000

Data Index: 608064 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2019. Min Act: -0.0000

Data Index: 337480 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.5282. Min Range: -1.5282

Max Act: 1.2687. Min Act: -0.0000

Data Index: 958839 (C4 (Web Text))

Max Activating Token Index: 69