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

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

Neuron 5072 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1274502 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3153. Min Act: 0.0000

Data Index: 1100618 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2793. Min Act: -0.0000

Data Index: 981236 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2839. Min Act: -0.0000

Data Index: 234504 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2755. Min Act: -0.0000

Data Index: 222613 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1231598 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1541963 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2545. Min Act: -0.0000

Data Index: 854740 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2796. Min Act: -0.0000

Data Index: 638615 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1014159 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2331. Min Act: -0.0000

Data Index: 752720 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2142. Min Act: -0.0000

Data Index: 250746 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1471486 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1517178 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1337696 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1522463 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2178. Min Act: -0.0000

Data Index: 390376 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2186. Min Act: -0.0000

Data Index: 722088 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2266. Min Act: -0.0000

Data Index: 889984 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1447193 (Python Code)

Max Activating Token Index: 897