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

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

Neuron 1015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5703. Min Act: -0.0001

Data Index: 1289776 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5634. Min Act: -0.0001

Data Index: 1204722 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.6368. Min Act: -0.0001

Data Index: 429096 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5873. Min Act: -0.0001

Data Index: 92545 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5824. Min Act: -0.0001

Data Index: 178478 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5796. Min Act: -0.0001

Data Index: 402221 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5605. Min Act: -0.0001

Data Index: 510737 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.4730. Min Act: -0.0001

Data Index: 711459 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.3937. Min Act: -0.0001

Data Index: 100271 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5493. Min Act: -0.0001

Data Index: 891143 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.4513. Min Act: -0.0001

Data Index: 413502 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.6227. Min Act: -0.0001

Data Index: 1274115 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5147. Min Act: -0.0001

Data Index: 330952 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5218. Min Act: -0.0001

Data Index: 241697 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5124. Min Act: -0.0001

Data Index: 702042 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5041. Min Act: -0.0001

Data Index: 877607 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.5033. Min Act: -0.0001

Data Index: 526034 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.4823. Min Act: -0.0001

Data Index: 884180 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.4833. Min Act: -0.0001

Data Index: 1076554 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.6368. Min Range: -1.6368

Max Act: 1.4851. Min Act: -0.0001

Data Index: 770149 (C4 (Web Text))

Max Activating Token Index: 692