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

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

Neuron 2059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2403. Min Act: -0.0002

Data Index: 42033 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.3775. Min Act: -0.0002

Data Index: 127159 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2929. Min Act: -0.0002

Data Index: 434679 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.4747. Min Act: -0.0002

Data Index: 486247 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2620. Min Act: -0.0002

Data Index: 824104 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2365. Min Act: -0.0002

Data Index: 714931 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.1268. Min Act: -0.0002

Data Index: 831343 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2920. Min Act: -0.0002

Data Index: 76823 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2161. Min Act: -0.0002

Data Index: 662778 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2419. Min Act: -0.0002

Data Index: 378653 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.4747. Min Range: -1.4747

Max Act: 0.8577. Min Act: -0.0002

Data Index: 513670 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.0823. Min Act: -0.0002

Data Index: 65673 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.2491. Min Act: -0.0002

Data Index: 655 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.0560. Min Act: -0.0002

Data Index: 682618 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 1.4747. Min Range: -1.4747

Max Act: 0.8371. Min Act: -0.0002

Data Index: 1323777 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.0406. Min Act: -0.0002

Data Index: 1070352 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.1517. Min Act: -0.0002

Data Index: 485512 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.1515. Min Act: -0.0002

Data Index: 335819 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.4747. Min Range: -1.4747

Max Act: 0.8965. Min Act: -0.0002

Data Index: 323816 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.4747. Min Range: -1.4747

Max Act: 1.0632. Min Act: -0.0002

Data Index: 253242 (C4 (Web Text))

Max Activating Token Index: 839