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

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

Neuron 1188 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.4395. Min Act: -0.0000

Data Index: 441071 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.4166. Min Act: -0.0000

Data Index: 250833 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1286139 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3975. Min Act: -0.0000

Data Index: 611995 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1262158 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3327. Min Act: -0.0000

Data Index: 170196 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3206. Min Act: -0.0000

Data Index: 382375 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3306. Min Act: -0.0000

Data Index: 55233 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1651117 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1083851 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1064277 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3103. Min Act: -0.0000

Data Index: 880218 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1535266 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.2846. Min Act: -0.0000

Data Index: 687864 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.3329. Min Act: -0.0000

Data Index: 127249 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1072199 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.2997. Min Act: -0.0000

Data Index: 885906 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1360403 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1353787 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.4395. Min Range: -0.4395

Max Act: 0.2998. Min Act: -0.0000

Data Index: 479567 (C4 (Web Text))

Max Activating Token Index: 920