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

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

Neuron 538 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: 0.0000

Data Index: 25018 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5508. Min Act: 0.0000

Data Index: 732016 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5345. Min Act: -0.0000

Data Index: 230499 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5335. Min Act: -0.0000

Data Index: 468095 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5156. Min Act: -0.0000

Data Index: 549000 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5114. Min Act: 0.0002

Data Index: 1289454 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4765. Min Act: -0.0000

Data Index: 335072 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1033676 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4443. Min Act: -0.0000

Data Index: 665061 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4387. Min Act: -0.0000

Data Index: 128571 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1004534 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4421. Min Act: 0.0000

Data Index: 1142218 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4405. Min Act: -0.0000

Data Index: 909182 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4262. Min Act: -0.0000

Data Index: 722113 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4264. Min Act: 0.0001

Data Index: 837412 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4349. Min Act: -0.0000

Data Index: 919210 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4280. Min Act: 0.0000

Data Index: 1110480 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4440. Min Act: 0.0000

Data Index: 370150 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4274. Min Act: 0.0001

Data Index: 322879 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1125699 (C4 (Web Text))

Max Activating Token Index: 250