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

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

Neuron 4004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.5740. Min Act: -0.0000

Data Index: 304476 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.5900. Min Act: -0.0000

Data Index: 877396 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.3407. Min Act: -0.0000

Data Index: 791475 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1472658 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1285793 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1443968 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1272549 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1821. Min Act: -0.0000

Data Index: 632526 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1129630 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.2154. Min Act: -0.0000

Data Index: 218816 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1025. Min Act: -0.0000

Data Index: 271159 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1992. Min Act: -0.0000

Data Index: 482297 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1604. Min Act: -0.0000

Data Index: 807878 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1077. Min Act: -0.0000

Data Index: 649176 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.0799. Min Act: -0.0000

Data Index: 661390 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1716. Min Act: -0.0000

Data Index: 984733 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1319. Min Act: -0.0000

Data Index: 653214 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1134. Min Act: -0.0000

Data Index: 498410 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 1.5900. Min Range: -1.5900

Max Act: 0.9085. Min Act: -0.0000

Data Index: 385314 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.5900. Min Range: -1.5900

Max Act: 1.1401. Min Act: -0.0000

Data Index: 747977 (C4 (Web Text))

Max Activating Token Index: 263