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

Dataset: The Pile

Neuron 1118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3261. Min Act: -0.0000

Data Index: 241636 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1890450 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2935. Min Act: -0.0000

Data Index: 768901 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1766011 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1844336 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1587656 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1282065 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2667. Min Act: -0.0000

Data Index: 98623 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1065467 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1106838 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2734. Min Act: -0.0000

Data Index: 454027 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2474. Min Act: -0.0000

Data Index: 763834 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1225441 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2573. Min Act: -0.0000

Data Index: 307241 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1082243 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2280. Min Act: -0.0000

Data Index: 52680 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1697985 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1680874 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1310054 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2434. Min Act: -0.0000

Data Index: 408204 (The Pile)

Max Activating Token Index: 97