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

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

Neuron 2950 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: 1.5885. Min Range: -1.5885

Max Act: 1.5885. Min Act: -0.0001

Data Index: 381472 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.5423. Min Act: -0.0001

Data Index: 559085 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.3411. Min Act: -0.0001

Data Index: 604318 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.3443. Min Act: -0.0001

Data Index: 19247 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.4365. Min Act: -0.0001

Data Index: 1120523 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1447. Min Act: -0.0001

Data Index: 209036 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1790. Min Act: -0.0001

Data Index: 312223 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1064. Min Act: -0.0001

Data Index: 909785 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0894. Min Act: -0.0001

Data Index: 397314 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1262613 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0154. Min Act: -0.0001

Data Index: 1300306 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0367. Min Act: -0.0001

Data Index: 885157 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.5885. Min Range: -1.5885

Max Act: 1.0448. Min Act: -0.0001

Data Index: 201454 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9440. Min Act: -0.0001

Data Index: 754661 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9705. Min Act: -0.0001

Data Index: 1344627 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9318. Min Act: -0.0001

Data Index: 926483 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9426. Min Act: -0.0001

Data Index: 602208 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9459. Min Act: -0.0001

Data Index: 246818 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9222. Min Act: -0.0001

Data Index: 1330354 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.5885. Min Range: -1.5885

Max Act: 0.9163. Min Act: -0.0001

Data Index: 1262037 (C4 (Web Text))

Max Activating Token Index: 56