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

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

Neuron 195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.6340. Min Act: -0.0000

Data Index: 518743 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.6204. Min Act: -0.0000

Data Index: 1342777 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3555. Min Act: -0.0000

Data Index: 1001923 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.4487. Min Act: -0.0000

Data Index: 1332175 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3527. Min Act: -0.0000

Data Index: 639995 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3467. Min Act: -0.0000

Data Index: 1073519 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3418. Min Act: -0.0000

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3306. Min Act: -0.0000

Data Index: 4201 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3407. Min Act: -0.0000

Data Index: 307647 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.3101. Min Act: -0.0000

Data Index: 837718 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.1001. Min Act: -0.0000

Data Index: 853379 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.2869. Min Act: -0.0000

Data Index: 1557593 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.0545. Min Act: -0.0000

Data Index: 272283 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.0486. Min Act: -0.0000

Data Index: 407828 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 2.6340. Min Range: -2.6340

Max Act: 1.9778. Min Act: -0.0000

Data Index: 966968 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.0712. Min Act: -0.0000

Data Index: 573335 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 2.6340. Min Range: -2.6340

Max Act: 1.9266. Min Act: -0.0000

Data Index: 225259 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.0262. Min Act: -0.0000

Data Index: 452876 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 2.6340. Min Range: -2.6340

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1193463 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.6340. Min Range: -2.6340

Max Act: 2.0079. Min Act: -0.0000

Data Index: 759328 (C4 (Web Text))

Max Activating Token Index: 962