Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1349807 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1298480 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1128915 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0644. Min Act: -0.0001

Data Index: 110296 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0693. Min Act: -0.0001

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1031371 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0601. Min Act: -0.0001

Data Index: 636429 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0644. Min Act: -0.0001

Data Index: 90431 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0577. Min Act: -0.0001

Data Index: 804174 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0527. Min Act: -0.0001

Data Index: 582874 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0549. Min Act: -0.0001

Data Index: 557618 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0546. Min Act: -0.0001

Data Index: 162580 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0557. Min Act: -0.0001

Data Index: 167968 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1015020 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0534. Min Act: -0.0001

Data Index: 667471 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0571. Min Act: -0.0001

Data Index: 826129 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0528. Min Act: -0.0001

Data Index: 491981 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1284219 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1199648 (C4 (Web Text))

Max Activating Token Index: 110