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

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

Neuron 1086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1296587 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3546. Min Act: -0.0001

Data Index: 85642 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3281. Min Act: -0.0001

Data Index: 414906 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1205752 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3065. Min Act: -0.0001

Data Index: 689989 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3030. Min Act: -0.0001

Data Index: 782418 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1227043 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3157. Min Act: -0.0001

Data Index: 1195414 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3382. Min Act: -0.0001

Data Index: 1234770 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3006. Min Act: -0.0001

Data Index: 86452 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2891. Min Act: -0.0001

Data Index: 407982 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2972. Min Act: -0.0001

Data Index: 952575 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3073. Min Act: -0.0001

Data Index: 773491 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3036. Min Act: -0.0001

Data Index: 655485 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3051. Min Act: -0.0001

Data Index: 583768 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2979. Min Act: -0.0001

Data Index: 172180 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2727. Min Act: -0.0001

Data Index: 466485 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2927. Min Act: -0.0001

Data Index: 24738 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2874. Min Act: -0.0001

Data Index: 437437 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2765. Min Act: -0.0001

Data Index: 1169375 (C4 (Web Text))

Max Activating Token Index: 1016