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

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

Neuron 2352 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: 2.1617. Min Range: -2.1617

Max Act: 2.1617. Min Act: -0.0002

Data Index: 201607 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 2.1617. Min Range: -2.1617

Max Act: 2.0453. Min Act: -0.0002

Data Index: 1056667 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.9967. Min Act: -0.0002

Data Index: 623385 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 2.1617. Min Range: -2.1617

Max Act: 2.0020. Min Act: -0.0002

Data Index: 948223 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.9880. Min Act: -0.0002

Data Index: 243677 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.9486. Min Act: -0.0002

Data Index: 400751 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.8148. Min Act: -0.0002

Data Index: 382884 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.8368. Min Act: -0.0002

Data Index: 242456 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.8086. Min Act: -0.0002

Data Index: 945977 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.8349. Min Act: -0.0002

Data Index: 404671 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.7450. Min Act: -0.0002

Data Index: 583365 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.7531. Min Act: -0.0002

Data Index: 1285750 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.7772. Min Act: -0.0002

Data Index: 207586 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6976. Min Act: -0.0002

Data Index: 764935 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6406. Min Act: -0.0002

Data Index: 430338 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6538. Min Act: -0.0002

Data Index: 926478 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6513. Min Act: -0.0002

Data Index: 433416 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6851. Min Act: -0.0002

Data Index: 759132 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6524. Min Act: -0.0002

Data Index: 135325 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 2.1617. Min Range: -2.1617

Max Act: 1.6353. Min Act: -0.0002

Data Index: 713165 (C4 (Web Text))

Max Activating Token Index: 124