Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4625 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1441. Min Range: -1.1441

Max Act: 1.1441. Min Act: -0.0000

Data Index: 159204 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.1441. Min Range: -1.1441

Max Act: 1.0686. Min Act: -0.0000

Data Index: 956509 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.1441. Min Range: -1.1441

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1129461 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1203284 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9709. Min Act: -0.0000

Data Index: 971946 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1300120 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8997. Min Act: -0.0000

Data Index: 434079 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1332121 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1003174 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8506. Min Act: -0.0000

Data Index: 552385 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8227. Min Act: -0.0000

Data Index: 435042 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8161. Min Act: -0.0000

Data Index: 528820 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8183. Min Act: -0.0000

Data Index: 564230 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8192. Min Act: -0.0000

Data Index: 769492 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1030871 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7580. Min Act: -0.0000

Data Index: 26133 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7588. Min Act: -0.0000

Data Index: 443823 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7826. Min Act: -0.0000

Data Index: 776785 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1072883 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8193. Min Act: -0.0000

Data Index: 774179 (C4 (Web Text))

Max Activating Token Index: 949