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

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

Neuron 3520 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0058. Min Range: -1.0058

Max Act: 1.0058. Min Act: -0.0000

Data Index: 106190 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.9913. Min Act: -0.0000

Data Index: 284072 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.9254. Min Act: -0.0000

Data Index: 713439 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.8495. Min Act: -0.0000

Data Index: 390340 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.9146. Min Act: -0.0000

Data Index: 873702 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1290956 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.8514. Min Act: -0.0000

Data Index: 697612 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1035517 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7871. Min Act: -0.0001

Data Index: 543128 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7731. Min Act: -0.0000

Data Index: 960067 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7639. Min Act: -0.0000

Data Index: 635351 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7833. Min Act: -0.0000

Data Index: 386643 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7283. Min Act: -0.0000

Data Index: 946554 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1083929 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7411. Min Act: -0.0000

Data Index: 378913 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1177942 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7079. Min Act: -0.0000

Data Index: 863068 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6924. Min Act: -0.0000

Data Index: 634482 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7044. Min Act: -0.0001

Data Index: 351755 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1326171 (C4 (Web Text))

Max Activating Token Index: 847