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

Dataset: The Pile

Neuron 1458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1128729 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1293284 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1758662 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1330358 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2530. Min Act: -0.0000

Data Index: 590073 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2550. Min Act: -0.0000

Data Index: 879933 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2626. Min Act: -0.0000

Data Index: 52481 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1975645 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1028321 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1688886 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1891741 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2345. Min Act: -0.0000

Data Index: 251023 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2394. Min Act: -0.0000

Data Index: 904175 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2463. Min Act: -0.0000

Data Index: 748226 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1320814 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2517. Min Act: -0.0000

Data Index: 711117 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1429368 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1091444 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1239606 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1742603 (The Pile)

Max Activating Token Index: 68