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

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

Neuron 3914 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: 0.6129. Min Range: -0.6129

Max Act: 0.6129. Min Act: -0.0000

Data Index: 9458 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.5276. Min Act: -0.0000

Data Index: 270062 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1279992 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4990. Min Act: -0.0000

Data Index: 217642 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1105731 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4668. Min Act: -0.0000

Data Index: 179160 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4518. Min Act: -0.0000

Data Index: 907187 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4627. Min Act: -0.0000

Data Index: 540784 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1280384 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4692. Min Act: -0.0000

Data Index: 980217 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4690. Min Act: -0.0000

Data Index: 151891 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4215. Min Act: -0.0000

Data Index: 897871 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4373. Min Act: -0.0000

Data Index: 118816 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4427. Min Act: -0.0000

Data Index: 751707 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4279. Min Act: -0.0000

Data Index: 630855 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4018. Min Act: -0.0000

Data Index: 909955 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4037. Min Act: -0.0000

Data Index: 119882 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4240. Min Act: -0.0000

Data Index: 720539 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3866. Min Act: -0.0000

Data Index: 606592 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1169933 (C4 (Web Text))

Max Activating Token Index: 806