Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1863 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2395. Min Range: -2.2395

Max Act: 2.2395. Min Act: -0.0000

Data Index: 674959 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.9347. Min Act: -0.0000

Data Index: 509645 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.9459. Min Act: -0.0000

Data Index: 105378 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.7788. Min Act: -0.0000

Data Index: 96479 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.8826. Min Act: -0.0000

Data Index: 969330 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.8515. Min Act: -0.0000

Data Index: 641538 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.6363. Min Act: -0.0000

Data Index: 816476 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.7294. Min Act: -0.0000

Data Index: 125380 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.6257. Min Act: -0.0000

Data Index: 353949 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.7210. Min Act: -0.0000

Data Index: 117487 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.6641. Min Act: -0.0000

Data Index: 170250 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.4498. Min Act: -0.0000

Data Index: 353329 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.6067. Min Act: -0.0000

Data Index: 1506070 (Python Code)

Max Activating Token Index: 174

Text #13

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1105477 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1289244 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.5965. Min Act: -0.0000

Data Index: 552944 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.5684. Min Act: -0.0000

Data Index: 826155 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1286778 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.4669. Min Act: -0.0000

Data Index: 679087 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 2.2395. Min Range: -2.2395

Max Act: 1.5608. Min Act: -0.0000

Data Index: 103012 (C4 (Web Text))

Max Activating Token Index: 427