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

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

Neuron 4209 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0336. Min Range: -2.0336

Max Act: 2.0336. Min Act: -0.0000

Data Index: 1331247 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.9174. Min Act: -0.0000

Data Index: 935844 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.6590. Min Act: -0.0000

Data Index: 692799 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.6331. Min Act: 0.0000

Data Index: 854975 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.5197. Min Act: -0.0000

Data Index: 246297 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.5120. Min Act: -0.0000

Data Index: 258848 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.5354. Min Act: -0.0000

Data Index: 394626 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.4270. Min Act: -0.0000

Data Index: 184406 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.4014. Min Act: -0.0000

Data Index: 866672 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.2870. Min Act: -0.0000

Data Index: 122350 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.3288. Min Act: -0.0000

Data Index: 212049 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.3329. Min Act: -0.0000

Data Index: 601247 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.3099. Min Act: -0.0000

Data Index: 574899 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.3036. Min Act: -0.0000

Data Index: 718112 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.2928. Min Act: -0.0000

Data Index: 580683 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1214621 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.2975. Min Act: -0.0000

Data Index: 1153602 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.2206. Min Act: -0.0000

Data Index: 107250 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.3456. Min Act: -0.0000

Data Index: 587042 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.0336. Min Range: -2.0336

Max Act: 1.2651. Min Act: -0.0000

Data Index: 259046 (C4 (Web Text))

Max Activating Token Index: 344