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

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

Neuron 4681 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: 1.6459. Min Range: -1.6459

Max Act: 1.5684. Min Act: -0.0001

Data Index: 1080839 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.6255. Min Act: -0.0001

Data Index: 375977 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.5752. Min Act: -0.0001

Data Index: 54952 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.4999. Min Act: -0.0001

Data Index: 422120 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.6459. Min Act: -0.0001

Data Index: 1019364 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.5333. Min Act: -0.0001

Data Index: 655097 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.5210. Min Act: -0.0001

Data Index: 225118 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.5002. Min Act: -0.0001

Data Index: 1043311 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.5249. Min Act: -0.0001

Data Index: 331962 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.4899. Min Act: -0.0001

Data Index: 463886 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.3467. Min Act: -0.0001

Data Index: 791645 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.3991. Min Act: -0.0001

Data Index: 802630 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.2932. Min Act: -0.0001

Data Index: 759323 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.3200. Min Act: -0.0001

Data Index: 1054811 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.4158. Min Act: -0.0001

Data Index: 1265616 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.4109. Min Act: -0.0001

Data Index: 286333 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.3601. Min Act: -0.0001

Data Index: 1105210 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.2991. Min Act: -0.0001

Data Index: 1293707 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.2626. Min Act: -0.0001

Data Index: 474031 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.2041. Min Act: -0.0001

Data Index: 43784 (C4 (Web Text))

Max Activating Token Index: 284