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

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

Neuron 3222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1269155 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.2735. Min Act: -0.0000

Data Index: 424955 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.4897. Min Act: -0.0000

Data Index: 1335577 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.2596. Min Act: -0.0000

Data Index: 408034 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.2230. Min Act: -0.0000

Data Index: 1173278 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.1993. Min Act: -0.0000

Data Index: 133914 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.9748. Min Act: -0.0000

Data Index: 630486 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.0391. Min Act: -0.0000

Data Index: 1313149 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.0670. Min Act: -0.0000

Data Index: 1235018 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 2.4897. Min Range: -2.4897

Max Act: 2.0425. Min Act: -0.0000

Data Index: 896716 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.7314. Min Act: -0.0000

Data Index: 751410 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.8339. Min Act: -0.0000

Data Index: 97689 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.6241. Min Act: -0.0000

Data Index: 867715 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1037572 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1192251 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.6848. Min Act: -0.0000

Data Index: 668908 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.3570. Min Act: -0.0000

Data Index: 150326 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.3667. Min Act: -0.0000

Data Index: 533318 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.3720. Min Act: -0.0000

Data Index: 700801 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.4897. Min Range: -2.4897

Max Act: 1.2723. Min Act: -0.0000

Data Index: 755876 (C4 (Web Text))

Max Activating Token Index: 54