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

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

Neuron 5069 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: 2.3386. Min Range: -2.3386

Max Act: 2.3386. Min Act: -0.0002

Data Index: 1095009 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.2540. Min Act: -0.0002

Data Index: 567924 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.2365. Min Act: -0.0002

Data Index: 363596 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.2462. Min Act: -0.0002

Data Index: 812451 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.2229. Min Act: -0.0002

Data Index: 700283 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.1865. Min Act: -0.0002

Data Index: 561269 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.1386. Min Act: -0.0002

Data Index: 1039543 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.1444. Min Act: -0.0002

Data Index: 102336 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.1268. Min Act: -0.0002

Data Index: 633369 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.0557. Min Act: -0.0002

Data Index: 1116183 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 2.3386. Min Range: -2.3386

Max Act: 2.1121. Min Act: -0.0002

Data Index: 1232954 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.9839. Min Act: -0.0002

Data Index: 388639 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.9990. Min Act: -0.0002

Data Index: 209223 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.9446. Min Act: -0.0002

Data Index: 295402 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.9229. Min Act: -0.0002

Data Index: 980496 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.9011. Min Act: -0.0002

Data Index: 41456 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.9015. Min Act: -0.0002

Data Index: 623521 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.8666. Min Act: -0.0002

Data Index: 1236919 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.8668. Min Act: -0.0002

Data Index: 1078694 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 2.3386. Min Range: -2.3386

Max Act: 1.8214. Min Act: -0.0002

Data Index: 393841 (C4 (Web Text))

Max Activating Token Index: 480