Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1556 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.9076. Min Act: -0.0001

Data Index: 941930 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.9852. Min Act: -0.0001

Data Index: 745675 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7974. Min Act: -0.0001

Data Index: 229307 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.8069. Min Act: -0.0001

Data Index: 80062 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7405. Min Act: -0.0001

Data Index: 292917 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7325. Min Act: -0.0001

Data Index: 322951 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1203130 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6470. Min Act: -0.0001

Data Index: 627644 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7012. Min Act: -0.0001

Data Index: 1284677 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6965. Min Act: -0.0001

Data Index: 550999 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6335. Min Act: -0.0001

Data Index: 139869 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6331. Min Act: -0.0001

Data Index: 515268 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6161. Min Act: -0.0001

Data Index: 327165 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1185515 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6203. Min Act: -0.0001

Data Index: 483137 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6242. Min Act: -0.0001

Data Index: 961273 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1139355 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1123493 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6508. Min Act: -0.0001

Data Index: 668777 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6150. Min Act: -0.0001

Data Index: 712570 (C4 (Web Text))

Max Activating Token Index: 317