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

Dataset: The Pile

Neuron 2553 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: 0.9083. Min Range: -0.9083

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1241323 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8953. Min Act: -0.0000

Data Index: 100107 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8378. Min Act: -0.0000

Data Index: 903073 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9083. Min Act: -0.0000

Data Index: 408642 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1303621 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1978234 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1245789 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1050224 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1838229 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7967. Min Act: -0.0000

Data Index: 107446 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1059877 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8148. Min Act: -0.0000

Data Index: 632172 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1818620 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7803. Min Act: -0.0000

Data Index: 353946 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7734. Min Act: -0.0000

Data Index: 744462 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1086698 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1261020 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1191243 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1360226 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1420132 (The Pile)

Max Activating Token Index: 912