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

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

Neuron 4455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1405. Min Range: -4.1405

Max Act: 4.1368. Min Act: -0.0000

Data Index: 81277 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 4.1405. Min Range: -4.1405

Max Act: 4.1405. Min Act: -0.0000

Data Index: 421275 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 4.1405. Min Range: -4.1405

Max Act: 4.1206. Min Act: -0.0000

Data Index: 533319 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 4.1405. Min Range: -4.1405

Max Act: 4.0771. Min Act: -0.0000

Data Index: 21522 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 4.1405. Min Range: -4.1405

Max Act: 4.0161. Min Act: -0.0000

Data Index: 1258821 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.9952. Min Act: -0.0000

Data Index: 447253 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.7992. Min Act: -0.0000

Data Index: 1071748 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.6835. Min Act: -0.0000

Data Index: 550803 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.6958. Min Act: -0.0000

Data Index: 246285 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.5226. Min Act: -0.0000

Data Index: 360661 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.6421. Min Act: -0.0000

Data Index: 1295717 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.4723. Min Act: -0.0000

Data Index: 651006 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.5744. Min Act: -0.0000

Data Index: 846374 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.5755. Min Act: -0.0000

Data Index: 40911 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.5794. Min Act: -0.0000

Data Index: 1039511 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.6067. Min Act: -0.0000

Data Index: 1187261 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.5933. Min Act: -0.0000

Data Index: 1011763 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.4651. Min Act: -0.0000

Data Index: 1195786 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.5615. Min Act: -0.0000

Data Index: 649084 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 4.1405. Min Range: -4.1405

Max Act: 3.4045. Min Act: -0.0000

Data Index: 965002 (C4 (Web Text))

Max Activating Token Index: 974