Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6225. Min Act: -0.0001

Data Index: 611162 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5793. Min Act: -0.0001

Data Index: 1118249 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6159. Min Act: -0.0001

Data Index: 257943 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5597. Min Act: -0.0001

Data Index: 400842 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1045882 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5735. Min Act: -0.0001

Data Index: 195294 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5577. Min Act: -0.0001

Data Index: 181060 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1226018 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5459. Min Act: -0.0001

Data Index: 84651 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5785. Min Act: -0.0001

Data Index: 840175 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5577. Min Act: -0.0001

Data Index: 541329 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5398. Min Act: -0.0001

Data Index: 122498 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5719. Min Act: -0.0001

Data Index: 483368 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5578. Min Act: -0.0001

Data Index: 189262 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5434. Min Act: -0.0001

Data Index: 219876 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5177. Min Act: -0.0001

Data Index: 880170 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1254110 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5706. Min Act: -0.0001

Data Index: 581259 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5378. Min Act: -0.0001

Data Index: 838349 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5330. Min Act: -0.0001

Data Index: 1154302 (C4 (Web Text))

Max Activating Token Index: 701