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

Dataset: The Pile

Neuron 395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4389. Min Act: -0.0000

Data Index: 653423 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4425. Min Act: -0.0000

Data Index: 59740 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1477961 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1272327 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3608. Min Act: -0.0000

Data Index: 949059 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3661. Min Act: -0.0000

Data Index: 928946 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1438128 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1539058 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1035602 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3439. Min Act: -0.0000

Data Index: 99407 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1925335 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1944088 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3103. Min Act: -0.0000

Data Index: 49677 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3287. Min Act: -0.0000

Data Index: 514515 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3289. Min Act: -0.0000

Data Index: 276820 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3027. Min Act: -0.0000

Data Index: 575380 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3216. Min Act: -0.0000

Data Index: 67107 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1146472 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3061. Min Act: -0.0000

Data Index: 695604 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2885. Min Act: -0.0000

Data Index: 124441 (The Pile)

Max Activating Token Index: 378