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

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

Neuron 2463 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.8712. Min Act: -0.0001

Data Index: 215035 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6549. Min Act: -0.0001

Data Index: 235615 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6931. Min Act: -0.0001

Data Index: 703469 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5898. Min Act: -0.0001

Data Index: 127076 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6526. Min Act: -0.0001

Data Index: 433858 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1340605 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1093014 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6232. Min Act: -0.0001

Data Index: 900868 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1358556 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5581. Min Act: -0.0001

Data Index: 399986 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5153. Min Act: -0.0001

Data Index: 498969 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5500. Min Act: -0.0001

Data Index: 1335552 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5574. Min Act: -0.0001

Data Index: 474446 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5460. Min Act: -0.0001

Data Index: 1152821 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1449739 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1388051 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1482959 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5580. Min Act: -0.0001

Data Index: 769691 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5134. Min Act: -0.0001

Data Index: 1149873 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1035186 (C4 (Web Text))

Max Activating Token Index: 364