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

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

Neuron 269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0299. Min Range: -3.0299

Max Act: 3.0299. Min Act: -0.0000

Data Index: 447254 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.7101. Min Act: -0.0000

Data Index: 543919 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.4303. Min Act: -0.0000

Data Index: 330999 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.3008. Min Act: -0.0000

Data Index: 878412 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.1946. Min Act: -0.0000

Data Index: 617291 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.1632. Min Act: -0.0000

Data Index: 603192 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.4798. Min Act: -0.0000

Data Index: 98430 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.2825. Min Act: -0.0000

Data Index: 740363 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.1376. Min Act: -0.0000

Data Index: 188025 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.0410. Min Act: -0.0000

Data Index: 597309 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.8030. Min Act: -0.0000

Data Index: 211021 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.8824. Min Act: -0.0000

Data Index: 189691 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.7288. Min Act: -0.0000

Data Index: 548960 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.0335. Min Act: -0.0000

Data Index: 950036 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.0246. Min Act: -0.0000

Data Index: 937007 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.9171. Min Act: -0.0000

Data Index: 532388 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 3.0299. Min Range: -3.0299

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1334325 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1148048 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.7311. Min Act: -0.0000

Data Index: 1167968 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 3.0299. Min Range: -3.0299

Max Act: 1.7251. Min Act: -0.0000

Data Index: 1034614 (C4 (Web Text))

Max Activating Token Index: 936