Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4975. Min Act: -0.0000

Data Index: 158593 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1907788 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1123313 (The Pile)

Max Activating Token Index: 260

Text #3

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1994523 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3387. Min Act: -0.0000

Data Index: 108996 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3464. Min Act: -0.0000

Data Index: 512037 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3392. Min Act: -0.0000

Data Index: 220491 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1056777 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3693. Min Act: -0.0000

Data Index: 374149 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1351668 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1184457 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1363811 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3016. Min Act: -0.0000

Data Index: 636640 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3199. Min Act: -0.0000

Data Index: 304830 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1011788 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1376831 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1332524 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1805750 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3094. Min Act: -0.0000

Data Index: 199775 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.4975. Min Range: -0.4975

Max Act: 0.3186. Min Act: -0.0000

Data Index: 694751 (The Pile)

Max Activating Token Index: 466