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

Dataset: The Pile

Neuron 728 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: 0.3385. Min Range: -0.3385

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1269186 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2862. Min Act: -0.0000

Data Index: 141823 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1169666 (The Pile)

Max Activating Token Index: 846

Text #3

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2854. Min Act: -0.0000

Data Index: 60874 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2928. Min Act: -0.0000

Data Index: 14544 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2478. Min Act: -0.0000

Data Index: 675678 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1464213 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2496. Min Act: -0.0000

Data Index: 372535 (The Pile)

Max Activating Token Index: 868

Text #8

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1901430 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1287079 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1167281 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2351. Min Act: -0.0000

Data Index: 8213 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1985756 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1963854 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1634680 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2403. Min Act: -0.0000

Data Index: 804786 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1963177 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2361. Min Act: -0.0000

Data Index: 178098 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1480174 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1359198 (The Pile)

Max Activating Token Index: 762