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

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

Neuron 3494 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0461. Min Range: -3.0461

Max Act: 3.0461. Min Act: -0.0000

Data Index: 1269834 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.8709. Min Act: -0.0001

Data Index: 39226 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.7122. Min Act: -0.0001

Data Index: 1273801 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.7507. Min Act: -0.0001

Data Index: 1107094 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.6131. Min Act: -0.0001

Data Index: 101516 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.3771. Min Act: -0.0000

Data Index: 494817 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.4841. Min Act: -0.0001

Data Index: 841580 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.5833. Min Act: -0.0000

Data Index: 1355477 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.4511. Min Act: -0.0001

Data Index: 1018557 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.4569. Min Act: -0.0001

Data Index: 283518 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.4381. Min Act: -0.0001

Data Index: 702083 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.4371. Min Act: -0.0000

Data Index: 1178475 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.3523. Min Act: -0.0001

Data Index: 378741 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.5083. Min Act: -0.0000

Data Index: 1130135 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.3684. Min Act: -0.0001

Data Index: 391926 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.3955. Min Act: -0.0001

Data Index: 158978 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.2645. Min Act: -0.0000

Data Index: 357395 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.4313. Min Act: -0.0000

Data Index: 8083 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.3092. Min Act: -0.0000

Data Index: 444681 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 3.0461. Min Range: -3.0461

Max Act: 2.3008. Min Act: -0.0001

Data Index: 1248184 (C4 (Web Text))

Max Activating Token Index: 65