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

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

Neuron 987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.5442. Min Act: -0.0001

Data Index: 938076 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.5160. Min Act: -0.0001

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4330. Min Act: -0.0001

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1256920 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4307. Min Act: -0.0001

Data Index: 521119 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4779. Min Act: -0.0001

Data Index: 204336 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4419. Min Act: -0.0001

Data Index: 533679 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4228. Min Act: -0.0001

Data Index: 201845 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4388. Min Act: -0.0001

Data Index: 48066 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1021183 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1199961 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1062353 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.3903. Min Act: -0.0001

Data Index: 499617 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.3713. Min Act: -0.0001

Data Index: 521263 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.3843. Min Act: -0.0000

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.3887. Min Act: -0.0001

Data Index: 1351949 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4314. Min Act: -0.0001

Data Index: 1065571 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.3828. Min Act: -0.0001

Data Index: 1152981 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.5442. Min Range: -0.5442

Max Act: 0.4227. Min Act: -0.0001

Data Index: 845761 (C4 (Web Text))

Max Activating Token Index: 943