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

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

Neuron 246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4616. Min Act: -0.0000

Data Index: 104717 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.0670. Min Act: -0.0000

Data Index: 723056 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.0333. Min Act: -0.0000

Data Index: 278649 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.0514. Min Act: -0.0000

Data Index: 735094 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.0026. Min Act: -0.0000

Data Index: 316083 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.9322. Min Act: -0.0000

Data Index: 149464 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.9915. Min Act: -0.0000

Data Index: 420104 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.9218. Min Act: -0.0000

Data Index: 518799 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8686. Min Act: -0.0000

Data Index: 261555 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.9577. Min Act: -0.0001

Data Index: 644545 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1597015 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1283930 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1274801 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1234561 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8557. Min Act: -0.0001

Data Index: 124139 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8653. Min Act: -0.0001

Data Index: 828063 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8856. Min Act: -0.0000

Data Index: 761205 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.9011. Min Act: -0.0001

Data Index: 1326608 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8065. Min Act: -0.0000

Data Index: 428076 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8307. Min Act: -0.0001

Data Index: 484171 (C4 (Web Text))

Max Activating Token Index: 595