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

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

Neuron 2273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0993. Min Range: -1.0993

Max Act: 1.0993. Min Act: -0.0000

Data Index: 408056 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.0993. Min Range: -1.0993

Max Act: 1.0550. Min Act: -0.0000

Data Index: 902797 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.0993. Min Range: -1.0993

Max Act: 1.0247. Min Act: -0.0000

Data Index: 337873 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9433. Min Act: -0.0000

Data Index: 967998 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9654. Min Act: -0.0000

Data Index: 319013 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9588. Min Act: -0.0000

Data Index: 332037 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9738. Min Act: -0.0000

Data Index: 29620 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9095. Min Act: -0.0000

Data Index: 158249 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9001. Min Act: -0.0000

Data Index: 859314 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9888. Min Act: -0.0000

Data Index: 442232 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9070. Min Act: -0.0000

Data Index: 930538 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.9039. Min Act: -0.0000

Data Index: 168196 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1214742 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.8678. Min Act: -0.0000

Data Index: 925485 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1568546 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.8395. Min Act: -0.0000

Data Index: 782460 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.8654. Min Act: -0.0000

Data Index: 932539 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.8524. Min Act: -0.0000

Data Index: 42514 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.8322. Min Act: -0.0000

Data Index: 114319 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.0993. Min Range: -1.0993

Max Act: 0.7661. Min Act: -0.0000

Data Index: 267337 (C4 (Web Text))

Max Activating Token Index: 215