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

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

Neuron 1449 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4808. Min Act: -0.0000

Data Index: 984415 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.5163. Min Act: -0.0001

Data Index: 121813 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1047870 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4475. Min Act: -0.0000

Data Index: 485911 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4117. Min Act: -0.0001

Data Index: 445886 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1054925 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3902. Min Act: -0.0000

Data Index: 8619 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3621. Min Act: -0.0000

Data Index: 68344 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3655. Min Act: -0.0001

Data Index: 698753 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3470. Min Act: -0.0000

Data Index: 241288 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3244. Min Act: -0.0001

Data Index: 834472 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1316571 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3450. Min Act: -0.0000

Data Index: 615320 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3181. Min Act: -0.0000

Data Index: 344618 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1001001 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1239065 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3436. Min Act: -0.0001

Data Index: 600528 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3289. Min Act: -0.0000

Data Index: 901245 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1082311 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3158. Min Act: -0.0001

Data Index: 514793 (C4 (Web Text))

Max Activating Token Index: 754