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

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

Neuron 4449 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.6984. Min Act: -0.0000

Data Index: 1161573 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.3123. Min Act: -0.0000

Data Index: 431386 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.2005. Min Act: -0.0000

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.3370. Min Act: -0.0000

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.2079. Min Act: -0.0000

Data Index: 1429795 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.1630. Min Act: -0.0000

Data Index: 685108 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0221. Min Act: -0.0000

Data Index: 524959 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.1037. Min Act: -0.0000

Data Index: 407625 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0902. Min Act: -0.0000

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 2.6984. Min Range: -2.6984

Max Act: 1.9401. Min Act: 0.0000

Data Index: 161639 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.6984. Min Range: -2.6984

Max Act: 1.9678. Min Act: -0.0000

Data Index: 299354 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0598. Min Act: -0.0000

Data Index: 959481 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0360. Min Act: -0.0000

Data Index: 971146 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0294. Min Act: -0.0000

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0237. Min Act: 0.0000

Data Index: 860648 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.1349. Min Act: -0.0000

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 2.6984. Min Range: -2.6984

Max Act: 1.9754. Min Act: -0.0000

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 2.6984. Min Range: -2.6984

Max Act: 1.9800. Min Act: -0.0000

Data Index: 521510 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0087. Min Act: -0.0000

Data Index: 984410 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.6984. Min Range: -2.6984

Max Act: 2.0274. Min Act: -0.0000

Data Index: 305360 (C4 (Web Text))

Max Activating Token Index: 780