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

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

Neuron 3045 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5494. Min Range: -5.5494

Max Act: 5.5494. Min Act: -0.0000

Data Index: 1149924 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.8454. Min Act: -0.0000

Data Index: 177520 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.9996. Min Act: -0.0000

Data Index: 503016 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 5.5494. Min Range: -5.5494

Max Act: 5.0291. Min Act: -0.0000

Data Index: 963401 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.9883. Min Act: -0.0000

Data Index: 900983 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.5566. Min Act: -0.0000

Data Index: 998581 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.9075. Min Act: -0.0000

Data Index: 1240877 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.4040. Min Act: -0.0000

Data Index: 194838 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.4458. Min Act: -0.0000

Data Index: 916183 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.3448. Min Act: -0.0000

Data Index: 189190 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.0875. Min Act: -0.0000

Data Index: 397996 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.2587. Min Act: -0.0000

Data Index: 445922 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.4370. Min Act: -0.0000

Data Index: 108566 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.2197. Min Act: -0.0000

Data Index: 254803 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.2058. Min Act: -0.0000

Data Index: 444433 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.1526. Min Act: -0.0000

Data Index: 969577 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.0806. Min Act: -0.0000

Data Index: 1246222 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.0533. Min Act: -0.0000

Data Index: 597967 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.2357. Min Act: -0.0000

Data Index: 410327 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 5.5494. Min Range: -5.5494

Max Act: 4.0715. Min Act: -0.0000

Data Index: 151768 (C4 (Web Text))

Max Activating Token Index: 212