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

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

Neuron 21 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1280659 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3224. Min Act: -0.0000

Data Index: 246116 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1136145 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.3173. Min Act: -0.0000

Data Index: 948790 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2512. Min Act: -0.0000

Data Index: 310499 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2423. Min Act: -0.0000

Data Index: 332078 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1273452 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2502. Min Act: -0.0000

Data Index: 980853 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2396. Min Act: -0.0000

Data Index: 851603 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2493. Min Act: -0.0000

Data Index: 859388 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2386. Min Act: -0.0000

Data Index: 159176 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2422. Min Act: -0.0000

Data Index: 473797 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2371. Min Act: -0.0000

Data Index: 372911 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2665. Min Act: -0.0000

Data Index: 373156 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2166. Min Act: -0.0000

Data Index: 27977 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2207. Min Act: -0.0000

Data Index: 295411 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2175. Min Act: -0.0000

Data Index: 349253 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1945. Min Act: -0.0000

Data Index: 484042 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.2001. Min Act: -0.0000

Data Index: 495925 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.3224. Min Range: -0.3224

Max Act: 0.1800. Min Act: -0.0000

Data Index: 428398 (C4 (Web Text))

Max Activating Token Index: 287