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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2810 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0001

Data Index: 708898 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1182. Min Act: -0.0001

Data Index: 325304 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1302652 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1093. Min Act: -0.0001

Data Index: 829939 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1163750 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1074. Min Act: -0.0001

Data Index: 413649 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1077. Min Act: -0.0001

Data Index: 412003 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1405904 (Python Code)

Max Activating Token Index: 992

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1171266 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0899. Min Act: -0.0001

Data Index: 289961 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1236986 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1080. Min Act: -0.0001

Data Index: 726708 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1082. Min Act: -0.0001

Data Index: 984231 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1507839 (Python Code)

Max Activating Token Index: 359

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1034. Min Act: -0.0001

Data Index: 645451 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0983. Min Act: -0.0001

Data Index: 763656 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1099. Min Act: -0.0001

Data Index: 739132 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1355156 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1046. Min Act: -0.0001

Data Index: 905422 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0970. Min Act: -0.0001

Data Index: 985618 (C4 (Web Text))

Max Activating Token Index: 711