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

Dataset: The Pile

Neuron 3344 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1339747 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2792. Min Act: -0.0000

Data Index: 443643 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3345. Min Act: -0.0000

Data Index: 756484 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1365839 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1886901 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1282388 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2606. Min Act: -0.0000

Data Index: 279820 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1963765 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2610. Min Act: -0.0000

Data Index: 932210 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1839212 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1615102 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.3032. Min Act: -0.0000

Data Index: 572901 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1553604 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1754013 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1446182 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2346. Min Act: -0.0000

Data Index: 627020 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2280. Min Act: -0.0000

Data Index: 664869 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1998178 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1179528 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 0.3345. Min Range: -0.3345

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1401537 (The Pile)

Max Activating Token Index: 311