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

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

Neuron 4703 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.2259. Min Act: -0.0001

Data Index: 920002 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1406. Min Act: -0.0001

Data Index: 956807 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.2133. Min Act: -0.0001

Data Index: 69114 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1131. Min Act: -0.0000

Data Index: 441020 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1033506 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1327. Min Act: -0.0001

Data Index: 1014576 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1082. Min Act: -0.0000

Data Index: 98671 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1194. Min Act: -0.0001

Data Index: 1176236 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0571. Min Act: -0.0000

Data Index: 805192 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1104. Min Act: -0.0001

Data Index: 572308 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0210. Min Act: -0.0001

Data Index: 624467 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0634. Min Act: -0.0001

Data Index: 1060173 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0046. Min Act: -0.0001

Data Index: 513993 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9950. Min Act: -0.0001

Data Index: 7283 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0865. Min Act: -0.0001

Data Index: 1182371 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0140. Min Act: -0.0001

Data Index: 533090 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0119. Min Act: -0.0001

Data Index: 1170538 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1194. Min Act: -0.0001

Data Index: 1216474 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1248617 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0008. Min Act: -0.0001

Data Index: 821292 (C4 (Web Text))

Max Activating Token Index: 899