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

Dataset: The Pile

Neuron 2626 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: 3.0406. Min Range: -3.0406

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1047186 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9245. Min Act: -0.0000

Data Index: 1330682 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.7257. Min Act: -0.0000

Data Index: 1814808 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.7448. Min Act: -0.0000

Data Index: 1583848 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 3.0406. Min Range: -3.0406

Max Act: 3.0406. Min Act: -0.0000

Data Index: 1414 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8869. Min Act: -0.0000

Data Index: 911034 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8455. Min Act: -0.0000

Data Index: 1594752 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6678. Min Act: -0.0000

Data Index: 1549787 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.7471. Min Act: -0.0000

Data Index: 532616 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 3.0406. Min Range: -3.0406

Max Act: 3.0343. Min Act: -0.0000

Data Index: 1589245 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.7651. Min Act: -0.0000

Data Index: 456540 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.7525. Min Act: -0.0000

Data Index: 849105 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6018. Min Act: -0.0000

Data Index: 337983 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6083. Min Act: -0.0000

Data Index: 51930 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.5731. Min Act: -0.0000

Data Index: 244567 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6930. Min Act: -0.0000

Data Index: 1842065 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6254. Min Act: -0.0000

Data Index: 1084841 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.5006. Min Act: -0.0000

Data Index: 1457047 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6277. Min Act: -0.0000

Data Index: 1728644 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.6053. Min Act: -0.0000

Data Index: 1344044 (The Pile)

Max Activating Token Index: 189