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

Dataset: The Pile

Neuron 1299 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: 1.6254. Min Range: -1.6254

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1774998 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1390074 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.4967. Min Act: -0.0000

Data Index: 60255 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3331. Min Act: -0.0000

Data Index: 360470 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3940. Min Act: -0.0000

Data Index: 926300 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1474879 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1988. Min Act: -0.0000

Data Index: 295671 (The Pile)

Max Activating Token Index: 398

Text #7

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1832. Min Act: -0.0000

Data Index: 787558 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1029646 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.0897. Min Act: -0.0000

Data Index: 101630 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1866774 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.0877. Min Act: -0.0000

Data Index: 218962 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1395886 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2186. Min Act: -0.0000

Data Index: 769490 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1801551 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.0330. Min Act: -0.0000

Data Index: 161200 (The Pile)

Max Activating Token Index: 4

Text #16

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1655969 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 1.6254. Min Range: -1.6254

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1917068 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 1.6254. Min Range: -1.6254

Max Act: 0.9740. Min Act: -0.0000

Data Index: 688045 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1933684 (The Pile)

Max Activating Token Index: 311