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

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

Neuron 877 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.7612. Min Act: -0.0001

Data Index: 731870 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6696. Min Act: -0.0001

Data Index: 811045 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.8514. Min Act: -0.0001

Data Index: 1306221 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.7204. Min Act: -0.0001

Data Index: 843670 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6492. Min Act: -0.0001

Data Index: 503706 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6004. Min Act: -0.0001

Data Index: 530680 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.5829. Min Act: -0.0001

Data Index: 155602 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.5701. Min Act: -0.0001

Data Index: 1294182 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6018. Min Act: -0.0001

Data Index: 137624 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.7201. Min Act: -0.0001

Data Index: 1009753 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6168. Min Act: -0.0001

Data Index: 440524 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6594. Min Act: -0.0001

Data Index: 838232 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6553. Min Act: -0.0001

Data Index: 153157 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.5958. Min Act: -0.0001

Data Index: 5410 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6321. Min Act: -0.0001

Data Index: 1347442 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6298. Min Act: -0.0001

Data Index: 1317969 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6093. Min Act: -0.0001

Data Index: 238845 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.5173. Min Act: -0.0001

Data Index: 1352873 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.6382. Min Act: -0.0001

Data Index: 201891 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 1.8514. Min Range: -1.8514

Max Act: 1.5219. Min Act: -0.0001

Data Index: 1324881 (C4 (Web Text))

Max Activating Token Index: 729