Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1875 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1328790 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.5730. Min Act: -0.0001

Data Index: 297744 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.6803. Min Act: -0.0001

Data Index: 1097663 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2766. Min Act: -0.0001

Data Index: 67332 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.5030. Min Act: -0.0001

Data Index: 164272 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3677. Min Act: -0.0001

Data Index: 1046780 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4379. Min Act: -0.0001

Data Index: 25724 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3323. Min Act: -0.0001

Data Index: 1254710 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4886. Min Act: -0.0001

Data Index: 90627 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3713. Min Act: -0.0001

Data Index: 1063240 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3043. Min Act: -0.0001

Data Index: 889278 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2243. Min Act: -0.0001

Data Index: 606403 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2920. Min Act: -0.0001

Data Index: 1093658 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2815. Min Act: -0.0001

Data Index: 424178 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2729. Min Act: -0.0001

Data Index: 476860 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2693. Min Act: -0.0001

Data Index: 498270 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2408. Min Act: -0.0001

Data Index: 565420 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3651. Min Act: -0.0001

Data Index: 1319385 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2949. Min Act: -0.0001

Data Index: 1245410 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.2141. Min Act: -0.0001

Data Index: 165562 (C4 (Web Text))

Max Activating Token Index: 427