Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.3432. Min Act: -0.0003

Data Index: 1224694 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.3886. Min Act: -0.0003

Data Index: 557575 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2894. Min Act: -0.0003

Data Index: 6769 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2415. Min Act: -0.0003

Data Index: 554306 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2125. Min Act: -0.0003

Data Index: 1003871 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2983. Min Act: -0.0003

Data Index: 1559245 (Python Code)

Max Activating Token Index: 552

Text #6

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2596. Min Act: -0.0003

Data Index: 424631 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2511. Min Act: -0.0003

Data Index: 272688 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.1965. Min Act: -0.0004

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2302. Min Act: -0.0003

Data Index: 596198 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2606. Min Act: -0.0003

Data Index: 988835 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2766. Min Act: -0.0003

Data Index: 1202217 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.1774. Min Act: -0.0003

Data Index: 442632 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2130. Min Act: -0.0003

Data Index: 475822 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.1684. Min Act: -0.0003

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.2044. Min Act: -0.0003

Data Index: 526327 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.1994. Min Act: -0.0003

Data Index: 205210 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.0951. Min Act: -0.0003

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.0940. Min Act: -0.0003

Data Index: 721260 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.3886. Min Range: -1.3886

Max Act: 1.1563. Min Act: -0.0003

Data Index: 463106 (C4 (Web Text))

Max Activating Token Index: 921