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

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

Neuron 5355 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.7188. Min Act: -0.0000

Data Index: 1282453 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.5544. Min Act: -0.0000

Data Index: 791906 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.5990. Min Act: -0.0000

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3915. Min Act: -0.0000

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3287. Min Act: -0.0000

Data Index: 1190034 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3480. Min Act: -0.0001

Data Index: 614479 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.5006. Min Act: -0.0000

Data Index: 654054 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.1230. Min Act: -0.0001

Data Index: 292797 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.1993. Min Act: -0.0000

Data Index: 644729 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.3685. Min Act: -0.0000

Data Index: 310000 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.1573. Min Act: -0.0001

Data Index: 883893 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.0985. Min Act: -0.0000

Data Index: 805852 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 4.7188. Min Range: -4.7188

Max Act: 4.0167. Min Act: -0.0000

Data Index: 182566 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.9887. Min Act: -0.0000

Data Index: 1288477 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.7095. Min Act: -0.0001

Data Index: 851270 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.7719. Min Act: -0.0000

Data Index: 1249694 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.6056. Min Act: -0.0000

Data Index: 978174 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.8280. Min Act: -0.0001

Data Index: 371089 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.8415. Min Act: -0.0000

Data Index: 415885 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 4.7188. Min Range: -4.7188

Max Act: 3.5215. Min Act: -0.0000

Data Index: 1023218 (C4 (Web Text))

Max Activating Token Index: 697