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

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

Neuron 4113 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: 1.1272. Min Range: -1.1272

Max Act: 1.1272. Min Act: -0.0000

Data Index: 30749 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.1272. Min Range: -1.1272

Max Act: 1.0901. Min Act: -0.0000

Data Index: 773793 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.1272. Min Range: -1.1272

Max Act: 1.0648. Min Act: -0.0000

Data Index: 851378 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.1272. Min Range: -1.1272

Max Act: 1.0476. Min Act: -0.0000

Data Index: 669380 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9958. Min Act: -0.0000

Data Index: 928949 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9924. Min Act: -0.0000

Data Index: 34623 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9085. Min Act: -0.0000

Data Index: 776532 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9131. Min Act: -0.0000

Data Index: 692566 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9750. Min Act: -0.0000

Data Index: 504675 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1154000 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1306006 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1151187 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.8200. Min Act: -0.0000

Data Index: 686628 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.8173. Min Act: -0.0000

Data Index: 295206 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.7614. Min Act: -0.0000

Data Index: 253453 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.8030. Min Act: -0.0000

Data Index: 411389 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.7531. Min Act: -0.0000

Data Index: 349938 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.6830. Min Act: -0.0000

Data Index: 148871 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1100723 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.1272. Min Range: -1.1272

Max Act: 0.7324. Min Act: -0.0000

Data Index: 145467 (C4 (Web Text))

Max Activating Token Index: 174