Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5171 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.5080. Min Act: -0.0001

Data Index: 1531094 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4570. Min Act: -0.0001

Data Index: 723758 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1520356 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4548. Min Act: -0.0001

Data Index: 270276 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4588. Min Act: -0.0001

Data Index: 571508 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4565. Min Act: -0.0001

Data Index: 1104878 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1463031 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4402. Min Act: -0.0001

Data Index: 836525 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1332864 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4338. Min Act: -0.0001

Data Index: 541736 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4359. Min Act: -0.0001

Data Index: 863603 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4293. Min Act: -0.0001

Data Index: 631791 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1199921 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4398. Min Act: -0.0001

Data Index: 291451 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4326. Min Act: -0.0001

Data Index: 406771 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4256. Min Act: -0.0001

Data Index: 475497 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4295. Min Act: -0.0001

Data Index: 1365721 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4203. Min Act: -0.0001

Data Index: 574759 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4166. Min Act: -0.0001

Data Index: 1047351 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4221. Min Act: -0.0001

Data Index: 1436946 (Python Code)

Max Activating Token Index: 80