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

Dataset: The Pile

Neuron 2218 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: 0.3232. Min Range: -0.3232

Max Act: 0.3232. Min Act: 0.0000

Data Index: 312058 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2693. Min Act: -0.0000

Data Index: 815330 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2856. Min Act: -0.0000

Data Index: 261776 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1447550 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1607524 (The Pile)

Max Activating Token Index: 946

Text #5

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2564. Min Act: 0.0000

Data Index: 732509 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1039357 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2555. Min Act: -0.0000

Data Index: 643977 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2493. Min Act: 0.0000

Data Index: 1819559 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1487562 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1036012 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2339. Min Act: -0.0000

Data Index: 242016 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2437. Min Act: -0.0000

Data Index: 571852 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2393. Min Act: -0.0000

Data Index: 772730 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2362. Min Act: 0.0000

Data Index: 761993 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1018306 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2276. Min Act: -0.0000

Data Index: 66460 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2330. Min Act: -0.0000

Data Index: 473300 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2344. Min Act: -0.0000

Data Index: 630466 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2305. Min Act: -0.0000

Data Index: 411856 (The Pile)

Max Activating Token Index: 266