Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.7163. Min Act: -0.0000

Data Index: 245355 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.5977. Min Act: -0.0000

Data Index: 725688 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.3145. Min Act: -0.0000

Data Index: 1178398 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.3372. Min Act: -0.0000

Data Index: 948393 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.4883. Min Act: -0.0000

Data Index: 595160 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.0678. Min Act: -0.0000

Data Index: 337068 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 6.7163. Min Range: -6.7163

Max Act: 6.0484. Min Act: -0.0000

Data Index: 541671 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.8561. Min Act: -0.0000

Data Index: 459402 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.8288. Min Act: -0.0000

Data Index: 1303814 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.8381. Min Act: -0.0000

Data Index: 182618 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.9637. Min Act: -0.0000

Data Index: 1080551 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.9331. Min Act: -0.0000

Data Index: 1273218 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.9630. Min Act: -0.0000

Data Index: 595225 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.9651. Min Act: -0.0000

Data Index: 254564 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.7277. Min Act: -0.0000

Data Index: 562676 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.8702. Min Act: -0.0000

Data Index: 1005305 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.3825. Min Act: -0.0000

Data Index: 1117820 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.5356. Min Act: -0.0000

Data Index: 718393 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.5563. Min Act: -0.0000

Data Index: 934481 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 6.7163. Min Range: -6.7163

Max Act: 5.7131. Min Act: -0.0000

Data Index: 427085 (C4 (Web Text))

Max Activating Token Index: 24