Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3729 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.1444. Min Act: -0.0001

Data Index: 1238834 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.1667. Min Act: -0.0001

Data Index: 1122335 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0995. Min Act: -0.0000

Data Index: 754998 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0946. Min Act: -0.0000

Data Index: 364537 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.1156. Min Act: -0.0001

Data Index: 1389067 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0749. Min Act: -0.0001

Data Index: 384644 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0601. Min Act: -0.0001

Data Index: 597419 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0726. Min Act: -0.0001

Data Index: 4634 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0656. Min Act: -0.0001

Data Index: 763314 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0618. Min Act: -0.0001

Data Index: 1428206 (Python Code)

Max Activating Token Index: 228

Text #10

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0528. Min Act: -0.0001

Data Index: 796882 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0808. Min Act: -0.0001

Data Index: 624060 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0134. Min Act: -0.0001

Data Index: 317132 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0696. Min Act: -0.0000

Data Index: 831289 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0393. Min Act: -0.0001

Data Index: 1566559 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0997. Min Act: -0.0001

Data Index: 1648850 (Python Code)

Max Activating Token Index: 904

Text #16

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0333. Min Act: -0.0001

Data Index: 778995 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0316. Min Act: -0.0001

Data Index: 143900 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9984. Min Act: -0.0001

Data Index: 1518955 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9481. Min Act: -0.0001

Data Index: 1504902 (Python Code)

Max Activating Token Index: 672