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

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

Neuron 3517 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: 0.3626. Min Range: -0.3626

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1134117 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1304863 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3626. Min Act: -0.0000

Data Index: 869738 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3287. Min Act: -0.0000

Data Index: 408166 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3172. Min Act: -0.0000

Data Index: 535071 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1041567 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3270. Min Act: -0.0001

Data Index: 569021 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3268. Min Act: -0.0001

Data Index: 739238 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3251. Min Act: -0.0000

Data Index: 16868 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3158. Min Act: -0.0000

Data Index: 772101 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3234. Min Act: -0.0000

Data Index: 989228 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3333. Min Act: -0.0000

Data Index: 340602 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3242. Min Act: -0.0000

Data Index: 8209 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3205. Min Act: -0.0000

Data Index: 852961 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3058. Min Act: -0.0000

Data Index: 741630 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1284680 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3100. Min Act: -0.0000

Data Index: 76334 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3081. Min Act: -0.0000

Data Index: 547383 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.3071. Min Act: -0.0001

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.3626. Min Range: -0.3626

Max Act: 0.2977. Min Act: -0.0001

Data Index: 892917 (C4 (Web Text))

Max Activating Token Index: 972