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

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

Neuron 2668 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: 0.6261. Min Range: -0.6261

Max Act: 0.6261. Min Act: -0.0000

Data Index: 608636 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4537. Min Act: -0.0001

Data Index: 684198 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4563. Min Act: -0.0001

Data Index: 601089 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1282163 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4061. Min Act: -0.0001

Data Index: 1493121 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4184. Min Act: -0.0001

Data Index: 133892 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1447546 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1342458 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1534071 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4256. Min Act: -0.0001

Data Index: 746849 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4139. Min Act: -0.0001

Data Index: 1408697 (Python Code)

Max Activating Token Index: 999

Text #12

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1587174 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.3736. Min Act: -0.0001

Data Index: 817116 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4216. Min Act: -0.0001

Data Index: 368367 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4240. Min Act: -0.0000

Data Index: 601293 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.3898. Min Act: -0.0001

Data Index: 1304003 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.3713. Min Act: -0.0001

Data Index: 451229 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4158. Min Act: -0.0001

Data Index: 1371349 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4123. Min Act: -0.0001

Data Index: 681578 (C4 (Web Text))

Max Activating Token Index: 607