Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3978. Min Act: -0.0001

Data Index: 578103 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3969. Min Act: -0.0001

Data Index: 372995 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3624. Min Act: -0.0001

Data Index: 13234 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3375. Min Act: -0.0001

Data Index: 1267965 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3511. Min Act: -0.0001

Data Index: 361182 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1088854 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3418. Min Act: -0.0001

Data Index: 1139188 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3470. Min Act: -0.0001

Data Index: 448580 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3280. Min Act: -0.0001

Data Index: 449425 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1333742 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3132. Min Act: -0.0001

Data Index: 593953 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3010. Min Act: -0.0001

Data Index: 484264 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3134. Min Act: -0.0001

Data Index: 693056 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3058. Min Act: -0.0000

Data Index: 90376 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3161. Min Act: -0.0001

Data Index: 206105 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1226629 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2773. Min Act: -0.0001

Data Index: 771645 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2894. Min Act: -0.0001

Data Index: 101382 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1150094 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.3978. Min Range: -0.3978

Max Act: 0.2904. Min Act: -0.0001

Data Index: 449077 (C4 (Web Text))

Max Activating Token Index: 412