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

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

Neuron 295 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0003

Data Index: 421628 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0505. Min Act: -0.0003

Data Index: 460985 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0504. Min Act: -0.0003

Data Index: 497597 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1075404 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0501. Min Act: -0.0003

Data Index: 770284 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0482. Min Act: -0.0003

Data Index: 243584 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1063348 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1246903 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0472. Min Act: -0.0003

Data Index: 15817 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0474. Min Act: -0.0003

Data Index: 786679 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0475. Min Act: -0.0003

Data Index: 95819 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0472. Min Act: -0.0003

Data Index: 247740 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0488. Min Act: -0.0003

Data Index: 340457 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0466. Min Act: -0.0003

Data Index: 809164 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0445. Min Act: -0.0003

Data Index: 173412 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0463. Min Act: -0.0004

Data Index: 215801 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1233843 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0459. Min Act: -0.0003

Data Index: 391357 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0459. Min Act: -0.0003

Data Index: 756016 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1003169 (C4 (Web Text))

Max Activating Token Index: 521