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

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

Neuron 4123 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: 1.4769. Min Range: -1.4769

Max Act: 1.4769. Min Act: -0.0000

Data Index: 447706 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.3348. Min Act: -0.0000

Data Index: 120239 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2433. Min Act: -0.0000

Data Index: 55760 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.3014. Min Act: -0.0000

Data Index: 141733 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2596. Min Act: -0.0000

Data Index: 518138 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2544. Min Act: -0.0000

Data Index: 353104 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1320675 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1135376 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1351451 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2317. Min Act: -0.0000

Data Index: 456455 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2126. Min Act: -0.0000

Data Index: 819630 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1062800 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1304128 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1181637 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2269. Min Act: -0.0000

Data Index: 667201 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.1613. Min Act: -0.0000

Data Index: 60862 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1092511 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1310315 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1027653 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.4769. Min Range: -1.4769

Max Act: 1.2100. Min Act: -0.0000

Data Index: 689714 (C4 (Web Text))

Max Activating Token Index: 699