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

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

Neuron 1327 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6265. Min Range: -3.6265

Max Act: 3.6265. Min Act: -0.0001

Data Index: 1329091 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.6265. Min Range: -3.6265

Max Act: 3.5234. Min Act: -0.0000

Data Index: 94552 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 3.6265. Min Range: -3.6265

Max Act: 3.3560. Min Act: -0.0000

Data Index: 501720 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.7136. Min Act: -0.0001

Data Index: 674754 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.9516. Min Act: -0.0000

Data Index: 790684 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.8996. Min Act: -0.0000

Data Index: 592385 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.8563. Min Act: -0.0000

Data Index: 1163077 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.4647. Min Act: -0.0000

Data Index: 551797 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.5143. Min Act: -0.0000

Data Index: 1327819 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.2847. Min Act: -0.0000

Data Index: 356912 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.3251. Min Act: -0.0000

Data Index: 884382 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.3982. Min Act: -0.0000

Data Index: 652492 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.1294. Min Act: -0.0001

Data Index: 785017 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.1170. Min Act: -0.0000

Data Index: 1034 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 3.6265. Min Range: -3.6265

Max Act: 1.9932. Min Act: -0.0000

Data Index: 908038 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.1727. Min Act: -0.0000

Data Index: 777184 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.1352. Min Act: -0.0000

Data Index: 938320 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.1008. Min Act: -0.0000

Data Index: 1296610 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.2532. Min Act: -0.0000

Data Index: 693508 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 3.6265. Min Range: -3.6265

Max Act: 2.0277. Min Act: -0.0000

Data Index: 1077690 (C4 (Web Text))

Max Activating Token Index: 483