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

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

Neuron 763 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: 0.5175. Min Range: -0.5175

Max Act: 0.5102. Min Act: -0.0001

Data Index: 930758 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.5175. Min Act: -0.0001

Data Index: 195754 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4757. Min Act: -0.0001

Data Index: 605550 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4883. Min Act: -0.0001

Data Index: 844191 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1205124 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4653. Min Act: -0.0001

Data Index: 1172106 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4705. Min Act: -0.0001

Data Index: 425221 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1240536 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4472. Min Act: -0.0001

Data Index: 125435 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4476. Min Act: -0.0001

Data Index: 559854 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4293. Min Act: -0.0001

Data Index: 938163 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1041652 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4349. Min Act: -0.0001

Data Index: 718598 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4329. Min Act: -0.0001

Data Index: 339155 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4159. Min Act: -0.0001

Data Index: 820580 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4295. Min Act: -0.0001

Data Index: 537152 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1580651 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4122. Min Act: -0.0001

Data Index: 233838 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4061. Min Act: -0.0001

Data Index: 622478 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1337512 (C4 (Web Text))

Max Activating Token Index: 608