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

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

Neuron 4563 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.9170. Min Act: -0.0000

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7491. Min Act: -0.0000

Data Index: 323281 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7409. Min Act: -0.0000

Data Index: 736548 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.7461. Min Act: -0.0000

Data Index: 896901 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5541. Min Act: -0.0000

Data Index: 240495 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6162. Min Act: -0.0000

Data Index: 154782 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5868. Min Act: -0.0000

Data Index: 167989 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5651. Min Act: -0.0000

Data Index: 156511 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1055593 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1004154 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5698. Min Act: -0.0000

Data Index: 891434 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.4986. Min Act: -0.0000

Data Index: 546093 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1018729 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5615. Min Act: -0.0000

Data Index: 114529 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5383. Min Act: -0.0000

Data Index: 972456 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1072183 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5545. Min Act: -0.0000

Data Index: 137632 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5642. Min Act: -0.0000

Data Index: 32936 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5596. Min Act: -0.0000

Data Index: 549770 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.9170. Min Range: -0.9170

Max Act: 0.5071. Min Act: -0.0000

Data Index: 958603 (C4 (Web Text))

Max Activating Token Index: 157