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

Dataset: The Pile

Neuron 2388 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: 0.5213. Min Range: -0.5213

Max Act: 0.5213. Min Act: -0.0000

Data Index: 879318 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1675025 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4397. Min Act: -0.0000

Data Index: 303958 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4464. Min Act: -0.0000

Data Index: 175187 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1659195 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1174050 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4083. Min Act: -0.0000

Data Index: 909713 (The Pile)

Max Activating Token Index: 147

Text #7

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1867563 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1540097 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1594994 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1956655 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1416256 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4115. Min Act: -0.0000

Data Index: 338585 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4083. Min Act: -0.0000

Data Index: 803972 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1442649 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4216. Min Act: -0.0000

Data Index: 526049 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4069. Min Act: -0.0000

Data Index: 264447 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4082. Min Act: -0.0000

Data Index: 781189 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4073. Min Act: -0.0000

Data Index: 182781 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1738351 (The Pile)

Max Activating Token Index: 169