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

Dataset: The Pile

Neuron 3262 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4303. Min Act: -0.0000

Data Index: 103134 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1111878 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4371. Min Act: -0.0000

Data Index: 447097 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4175. Min Act: -0.0000

Data Index: 888116 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3763. Min Act: -0.0000

Data Index: 98095 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1553628 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3516. Min Act: -0.0000

Data Index: 392734 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3202. Min Act: -0.0000

Data Index: 461578 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1530001 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3443. Min Act: -0.0000

Data Index: 974143 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1573890 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1460048 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3076. Min Act: -0.0000

Data Index: 234293 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3036. Min Act: -0.0000

Data Index: 885716 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1962601 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3100. Min Act: -0.0000

Data Index: 119667 (The Pile)

Max Activating Token Index: 310

Text #16

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1837183 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1264611 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1843713 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3011. Min Act: -0.0000

Data Index: 344652 (The Pile)

Max Activating Token Index: 365