Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3256. Min Range: -5.3256

Max Act: 5.0280. Min Act: -0.0001

Data Index: 650168 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 5.3256. Min Range: -5.3256

Max Act: 5.3256. Min Act: -0.0001

Data Index: 398507 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.5714. Min Act: -0.0001

Data Index: 369656 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.5286. Min Act: -0.0001

Data Index: 661807 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.3798. Min Act: -0.0001

Data Index: 522093 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.3893. Min Act: -0.0001

Data Index: 140803 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.1877. Min Act: -0.0001

Data Index: 1169277 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.6303. Min Act: -0.0001

Data Index: 675406 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.1165. Min Act: -0.0001

Data Index: 1299672 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.2041. Min Act: -0.0001

Data Index: 1160740 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.2861. Min Act: -0.0001

Data Index: 675718 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.6289. Min Act: -0.0001

Data Index: 1177532 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.0563. Min Act: -0.0001

Data Index: 377376 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 5.3256. Min Range: -5.3256

Max Act: 3.7933. Min Act: -0.0001

Data Index: 322817 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.1186. Min Act: -0.0001

Data Index: 616123 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 5.3256. Min Range: -5.3256

Max Act: 3.7707. Min Act: -0.0001

Data Index: 361575 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 5.3256. Min Range: -5.3256

Max Act: 3.4221. Min Act: -0.0001

Data Index: 711556 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 5.3256. Min Range: -5.3256

Max Act: 3.8755. Min Act: -0.0001

Data Index: 1269745 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 5.3256. Min Range: -5.3256

Max Act: 4.1123. Min Act: -0.0001

Data Index: 1294387 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 5.3256. Min Range: -5.3256

Max Act: 3.8435. Min Act: -0.0001

Data Index: 957509 (C4 (Web Text))

Max Activating Token Index: 298