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

Dataset: The Pile

Neuron 4284 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: 0.2920. Min Range: -0.2920

Max Act: 0.2920. Min Act: -0.0000

Data Index: 128640 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1147452 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2736. Min Act: -0.0000

Data Index: 950692 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1608129 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2598. Min Act: -0.0000

Data Index: 11888 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2572. Min Act: -0.0000

Data Index: 549252 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1527475 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1826213 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1184493 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2386. Min Act: -0.0000

Data Index: 598153 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2461. Min Act: -0.0000

Data Index: 817254 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2451. Min Act: -0.0000

Data Index: 889301 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2272. Min Act: -0.0000

Data Index: 813488 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2313. Min Act: -0.0000

Data Index: 780366 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2294. Min Act: -0.0000

Data Index: 652124 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1093887 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2276. Min Act: -0.0000

Data Index: 906019 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1377224 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2259. Min Act: -0.0000

Data Index: 25499 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1249673 (The Pile)

Max Activating Token Index: 1020