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

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

Neuron 1802 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.9198. Min Act: -0.0001

Data Index: 1262517 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7345. Min Act: -0.0001

Data Index: 364090 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7681. Min Act: -0.0001

Data Index: 998244 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6984. Min Act: -0.0001

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6922. Min Act: -0.0001

Data Index: 1209184 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7111. Min Act: -0.0001

Data Index: 824618 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6040. Min Act: -0.0001

Data Index: 833100 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1063621 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6095. Min Act: -0.0001

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6288. Min Act: -0.0001

Data Index: 705276 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6254. Min Act: -0.0001

Data Index: 582446 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6049. Min Act: -0.0001

Data Index: 288451 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6163. Min Act: -0.0001

Data Index: 526193 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6125. Min Act: -0.0001

Data Index: 221294 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6243. Min Act: -0.0001

Data Index: 1051834 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5782. Min Act: -0.0001

Data Index: 1194848 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5815. Min Act: -0.0001

Data Index: 179889 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6009. Min Act: -0.0001

Data Index: 819845 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5480. Min Act: -0.0001

Data Index: 395261 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5498. Min Act: -0.0001

Data Index: 494762 (C4 (Web Text))

Max Activating Token Index: 454