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

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

Neuron 1304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0001

Data Index: 849139 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0655. Min Act: -0.0001

Data Index: 712797 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0591. Min Act: -0.0000

Data Index: 977324 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0641. Min Act: -0.0001

Data Index: 898271 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0591. Min Act: -0.0000

Data Index: 924997 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1504528 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1300038 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1546234 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1479001 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1447004 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0528. Min Act: -0.0000

Data Index: 974667 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0510. Min Act: -0.0000

Data Index: 678677 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0505. Min Act: -0.0001

Data Index: 945027 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0503. Min Act: -0.0000

Data Index: 96876 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0515. Min Act: -0.0000

Data Index: 127919 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1232966 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1151436 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0479. Min Act: -0.0000

Data Index: 800947 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0491. Min Act: -0.0001

Data Index: 525822 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1081468 (C4 (Web Text))

Max Activating Token Index: 616