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

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

Neuron 3093 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2879. Min Act: -0.0001

Data Index: 250393 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2899. Min Act: -0.0001

Data Index: 983964 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2681. Min Act: -0.0001

Data Index: 567618 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2735. Min Act: -0.0001

Data Index: 591018 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2428. Min Act: -0.0001

Data Index: 16094 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2456. Min Act: -0.0001

Data Index: 999472 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2462. Min Act: -0.0001

Data Index: 386405 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1148212 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2292. Min Act: -0.0001

Data Index: 392233 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2358. Min Act: -0.0001

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2381. Min Act: -0.0001

Data Index: 594706 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2305. Min Act: -0.0001

Data Index: 609805 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2285. Min Act: -0.0001

Data Index: 862788 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2835. Min Act: -0.0001

Data Index: 1103249 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2351. Min Act: -0.0001

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2321. Min Act: -0.0001

Data Index: 233832 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2202. Min Act: -0.0001

Data Index: 331399 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2398. Min Act: -0.0001

Data Index: 787116 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2212. Min Act: -0.0001

Data Index: 549140 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1070008 (C4 (Web Text))

Max Activating Token Index: 603