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

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

Neuron 3626 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: 1.0041. Min Range: -1.0041

Max Act: 1.0011. Min Act: -0.0002

Data Index: 1305798 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9967. Min Act: -0.0002

Data Index: 230899 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.0041. Min Range: -1.0041

Max Act: 1.0041. Min Act: -0.0002

Data Index: 812783 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9963. Min Act: -0.0002

Data Index: 317123 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9648. Min Act: -0.0002

Data Index: 1323734 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9949. Min Act: -0.0003

Data Index: 783440 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9914. Min Act: -0.0002

Data Index: 56335 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9601. Min Act: -0.0002

Data Index: 1062681 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9614. Min Act: -0.0002

Data Index: 953496 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9621. Min Act: -0.0002

Data Index: 554018 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9392. Min Act: -0.0002

Data Index: 1343004 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9538. Min Act: -0.0002

Data Index: 671888 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9472. Min Act: -0.0002

Data Index: 149893 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9363. Min Act: -0.0002

Data Index: 644347 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9402. Min Act: -0.0002

Data Index: 686128 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9203. Min Act: -0.0002

Data Index: 275920 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9309. Min Act: -0.0002

Data Index: 1309472 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9072. Min Act: -0.0002

Data Index: 1318546 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9332. Min Act: -0.0002

Data Index: 352055 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9188. Min Act: -0.0002

Data Index: 704115 (C4 (Web Text))

Max Activating Token Index: 796