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

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

Neuron 4457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1001. Min Range: -2.1001

Max Act: 2.0010. Min Act: -0.0000

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 2.1001. Min Range: -2.1001

Max Act: 2.1001. Min Act: -0.0000

Data Index: 872742 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 2.1001. Min Range: -2.1001

Max Act: 2.0266. Min Act: -0.0001

Data Index: 1143761 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.9052. Min Act: -0.0001

Data Index: 365835 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.9681. Min Act: -0.0001

Data Index: 254103 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.9346. Min Act: -0.0001

Data Index: 884961 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.7927. Min Act: -0.0001

Data Index: 641494 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.8770. Min Act: -0.0000

Data Index: 337627 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.7460. Min Act: -0.0001

Data Index: 681681 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.8278. Min Act: -0.0000

Data Index: 566203 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.5811. Min Act: -0.0001

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.7006. Min Act: -0.0000

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.6080. Min Act: -0.0001

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.5080. Min Act: -0.0001

Data Index: 813953 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.6354. Min Act: -0.0001

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.4882. Min Act: -0.0001

Data Index: 679466 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.3206. Min Act: -0.0001

Data Index: 1210868 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1262557 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.4228. Min Act: -0.0001

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 2.1001. Min Range: -2.1001

Max Act: 1.2389. Min Act: -0.0001

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 739