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

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

Neuron 4038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.9123. Min Act: -0.0001

Data Index: 44570 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7423. Min Act: -0.0000

Data Index: 411536 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7144. Min Act: -0.0000

Data Index: 902917 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7060. Min Act: -0.0000

Data Index: 996105 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6394. Min Act: -0.0000

Data Index: 538881 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6549. Min Act: -0.0001

Data Index: 278969 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1112869 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1276642 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6485. Min Act: -0.0000

Data Index: 416515 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.5896. Min Act: -0.0001

Data Index: 833211 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6474. Min Act: -0.0000

Data Index: 837138 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6452. Min Act: -0.0001

Data Index: 861774 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1010262 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6142. Min Act: -0.0000

Data Index: 152696 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6310. Min Act: -0.0000

Data Index: 679121 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.5436. Min Act: -0.0000

Data Index: 197475 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1269487 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6550. Min Act: -0.0001

Data Index: 110849 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.5977. Min Act: -0.0000

Data Index: 69254 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1122603 (C4 (Web Text))

Max Activating Token Index: 937