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

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

Neuron 3183 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.6457. Min Act: -0.0000

Data Index: 127514 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.6140. Min Act: -0.0000

Data Index: 459942 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5766. Min Act: -0.0001

Data Index: 160971 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5434. Min Act: -0.0000

Data Index: 465642 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1349073 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5353. Min Act: -0.0000

Data Index: 916224 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5161. Min Act: -0.0000

Data Index: 116488 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1113535 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4906. Min Act: -0.0000

Data Index: 707900 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4748. Min Act: -0.0001

Data Index: 550023 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1187537 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1288979 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4513. Min Act: -0.0000

Data Index: 25332 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4596. Min Act: -0.0000

Data Index: 553877 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4346. Min Act: -0.0000

Data Index: 855573 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4306. Min Act: -0.0000

Data Index: 381901 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4464. Min Act: -0.0000

Data Index: 509054 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1227989 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1019297 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4531. Min Act: -0.0000

Data Index: 223809 (C4 (Web Text))

Max Activating Token Index: 402