Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3248 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.9184. Min Range: -6.9184

Max Act: 6.9184. Min Act: -0.0000

Data Index: 1354803 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 6.9184. Min Range: -6.9184

Max Act: 6.1622. Min Act: -0.0000

Data Index: 853537 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.6275. Min Act: -0.0000

Data Index: 465243 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.0821. Min Act: -0.0000

Data Index: 389048 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.8131. Min Act: -0.0000

Data Index: 589323 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.6123. Min Act: -0.0000

Data Index: 52312 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.3474. Min Act: -0.0000

Data Index: 866831 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.4619. Min Act: -0.0000

Data Index: 499512 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.2372. Min Act: -0.0000

Data Index: 117454 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.0517. Min Act: -0.0000

Data Index: 9065 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.3212. Min Act: -0.0000

Data Index: 672328 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 6.9184. Min Range: -6.9184

Max Act: 5.2342. Min Act: -0.0000

Data Index: 719049 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.6168. Min Act: -0.0000

Data Index: 213085 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.9406. Min Act: -0.0000

Data Index: 1086177 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.6947. Min Act: -0.0000

Data Index: 522916 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.8155. Min Act: -0.0000

Data Index: 75969 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.7671. Min Act: -0.0000

Data Index: 85630 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.5720. Min Act: -0.0000

Data Index: 482700 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.5926. Min Act: -0.0000

Data Index: 1126868 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 6.9184. Min Range: -6.9184

Max Act: 4.4916. Min Act: -0.0000

Data Index: 274757 (C4 (Web Text))

Max Activating Token Index: 962