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

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

Neuron 3574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3245. Min Act: -0.0000

Data Index: 664161 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3165. Min Act: -0.0001

Data Index: 493810 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1233529 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2748. Min Act: -0.0001

Data Index: 336411 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3138. Min Act: -0.0000

Data Index: 942412 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2862. Min Act: -0.0001

Data Index: 68111 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1084988 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1145372 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2765. Min Act: -0.0001

Data Index: 605469 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2570. Min Act: -0.0001

Data Index: 97556 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2795. Min Act: -0.0001

Data Index: 229930 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2765. Min Act: -0.0000

Data Index: 236300 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2565. Min Act: -0.0001

Data Index: 79089 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2542. Min Act: -0.0000

Data Index: 569002 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2522. Min Act: -0.0000

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1026625 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2444. Min Act: -0.0001

Data Index: 754960 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2433. Min Act: -0.0000

Data Index: 845063 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2539. Min Act: -0.0001

Data Index: 1148809 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.2570. Min Act: -0.0000

Data Index: 262066 (C4 (Web Text))

Max Activating Token Index: 994