Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.3168. Min Act: -0.0001

Data Index: 626775 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2835. Min Act: -0.0001

Data Index: 1171157 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2771. Min Act: -0.0001

Data Index: 274211 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1240432 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2140. Min Act: -0.0001

Data Index: 307264 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2570. Min Act: -0.0001

Data Index: 299845 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2612. Min Act: -0.0001

Data Index: 301400 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2530. Min Act: -0.0001

Data Index: 97202 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2564. Min Act: -0.0001

Data Index: 1241572 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2331. Min Act: -0.0001

Data Index: 485632 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2543. Min Act: -0.0001

Data Index: 727175 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1349375 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2323. Min Act: -0.0001

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2387. Min Act: -0.0001

Data Index: 1365439 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1257171 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2371. Min Act: -0.0001

Data Index: 1200278 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2380. Min Act: -0.0001

Data Index: 924217 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2127. Min Act: -0.0001

Data Index: 73716 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2462. Min Act: -0.0001

Data Index: 742252 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1211189 (C4 (Web Text))

Max Activating Token Index: 23