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

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

Neuron 1551 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9485. Min Act: -0.0002

Data Index: 104329 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0002

Data Index: 841370 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9034. Min Act: -0.0002

Data Index: 958984 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9098. Min Act: -0.0002

Data Index: 1290617 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9220. Min Act: -0.0002

Data Index: 1226847 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9137. Min Act: -0.0003

Data Index: 1332035 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9021. Min Act: -0.0002

Data Index: 96739 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8839. Min Act: -0.0002

Data Index: 1380101 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9037. Min Act: -0.0002

Data Index: 944497 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8867. Min Act: -0.0002

Data Index: 1062038 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8573. Min Act: -0.0002

Data Index: 396017 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8537. Min Act: -0.0002

Data Index: 777968 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8392. Min Act: -0.0002

Data Index: 1308526 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8571. Min Act: -0.0002

Data Index: 468199 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8469. Min Act: -0.0002

Data Index: 1019437 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8574. Min Act: -0.0003

Data Index: 386653 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8479. Min Act: -0.0002

Data Index: 1471496 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8567. Min Act: -0.0002

Data Index: 97131 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8341. Min Act: -0.0002

Data Index: 1140917 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8346. Min Act: -0.0002

Data Index: 775089 (C4 (Web Text))

Max Activating Token Index: 635