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

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

Neuron 1824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.5207. Min Act: -0.0001

Data Index: 1108884 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.3512. Min Act: -0.0001

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.9494. Min Act: -0.0001

Data Index: 1181574 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.5245. Min Act: -0.0001

Data Index: 310076 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.7004. Min Act: -0.0001

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.5770. Min Act: -0.0001

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.6280. Min Act: -0.0001

Data Index: 1341459 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.7066. Min Act: -0.0001

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.6675. Min Act: -0.0001

Data Index: 964781 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.4438. Min Act: -0.0001

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.2504. Min Act: -0.0001

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.3784. Min Act: -0.0001

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.2549. Min Act: -0.0001

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.4885. Min Act: -0.0001

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.4763. Min Act: -0.0001

Data Index: 1208391 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.3082. Min Act: -0.0001

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.2716. Min Act: -0.0001

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.4910. Min Act: -0.0001

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.2443. Min Act: -0.0001

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.2146. Min Act: -0.0001

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 55