Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3371 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.8118. Min Act: -0.0001

Data Index: 674282 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.7264. Min Act: -0.0001

Data Index: 1252979 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.7000. Min Act: -0.0001

Data Index: 350766 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6442. Min Act: -0.0001

Data Index: 936833 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.7212. Min Act: -0.0001

Data Index: 1098388 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6898. Min Act: -0.0001

Data Index: 957087 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6052. Min Act: -0.0001

Data Index: 482562 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6385. Min Act: -0.0001

Data Index: 153069 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6304. Min Act: -0.0001

Data Index: 623915 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6484. Min Act: -0.0001

Data Index: 25494 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.6070. Min Act: -0.0001

Data Index: 1319606 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5251. Min Act: -0.0001

Data Index: 156474 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5679. Min Act: -0.0001

Data Index: 1357906 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5958. Min Act: -0.0001

Data Index: 1161380 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5853. Min Act: -0.0001

Data Index: 671882 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5810. Min Act: -0.0001

Data Index: 708865 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5722. Min Act: -0.0001

Data Index: 306463 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5566. Min Act: -0.0001

Data Index: 130178 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5552. Min Act: -0.0001

Data Index: 781270 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.8118. Min Range: -1.8118

Max Act: 1.5953. Min Act: -0.0001

Data Index: 477228 (C4 (Web Text))

Max Activating Token Index: 197