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

Dataset: The Pile

Neuron 3924 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.4209. Min Act: -0.0000

Data Index: 478405 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.6388. Min Act: -0.0000

Data Index: 1566716 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.3180. Min Act: -0.0000

Data Index: 1005003 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.6500. Min Act: -0.0000

Data Index: 1848146 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.4357. Min Act: -0.0000

Data Index: 336439 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.9869. Min Act: -0.0000

Data Index: 1780417 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.2480. Min Act: -0.0000

Data Index: 1209144 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.0610. Min Act: -0.0000

Data Index: 932172 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 3.6500. Min Range: -3.6500

Max Act: 3.0296. Min Act: -0.0000

Data Index: 320436 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.9791. Min Act: -0.0000

Data Index: 1584041 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.7409. Min Act: -0.0000

Data Index: 17316 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.9197. Min Act: -0.0000

Data Index: 1665168 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.8866. Min Act: -0.0000

Data Index: 1413075 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.7142. Min Act: -0.0000

Data Index: 1210010 (The Pile)

Max Activating Token Index: 387

Text #14

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.9726. Min Act: -0.0000

Data Index: 710517 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.8105. Min Act: -0.0000

Data Index: 1074207 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.6491. Min Act: -0.0000

Data Index: 1970726 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.7943. Min Act: -0.0000

Data Index: 1872436 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.6561. Min Act: -0.0000

Data Index: 465526 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 3.6500. Min Range: -3.6500

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1797434 (The Pile)

Max Activating Token Index: 596