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

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

Neuron 907 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: 1.4441. Min Range: -1.4441

Max Act: 1.4441. Min Act: -0.0001

Data Index: 367107 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3679. Min Act: -0.0001

Data Index: 1026638 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3146. Min Act: -0.0001

Data Index: 70431 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1916. Min Act: -0.0001

Data Index: 340000 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1469. Min Act: -0.0001

Data Index: 295335 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0550. Min Act: -0.0001

Data Index: 578069 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9612. Min Act: -0.0001

Data Index: 725934 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1209. Min Act: -0.0001

Data Index: 599269 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0445. Min Act: -0.0001

Data Index: 1485954 (Python Code)

Max Activating Token Index: 840

Text #9

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0388. Min Act: -0.0001

Data Index: 513388 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9364. Min Act: -0.0001

Data Index: 1537561 (Python Code)

Max Activating Token Index: 755

Text #11

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0590. Min Act: -0.0001

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9993. Min Act: -0.0001

Data Index: 916305 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9856. Min Act: -0.0001

Data Index: 297271 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0856. Min Act: -0.0001

Data Index: 814902 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0028. Min Act: -0.0001

Data Index: 899650 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9424. Min Act: -0.0001

Data Index: 98219 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.8415. Min Act: -0.0001

Data Index: 314374 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0097. Min Act: -0.0001

Data Index: 416633 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9572. Min Act: -0.0001

Data Index: 463143 (C4 (Web Text))

Max Activating Token Index: 792