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

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

Neuron 3859 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: 0.4030. Min Range: -0.4030

Max Act: 0.4030. Min Act: -0.0001

Data Index: 1340376 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1268458 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1344831 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1353797 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3825. Min Act: -0.0001

Data Index: 430378 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3356. Min Act: -0.0001

Data Index: 682742 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3346. Min Act: -0.0001

Data Index: 808126 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2824. Min Act: -0.0001

Data Index: 386827 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3535. Min Act: -0.0001

Data Index: 709682 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1089213 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3086. Min Act: -0.0001

Data Index: 68487 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3307. Min Act: -0.0001

Data Index: 648984 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3069. Min Act: -0.0001

Data Index: 706303 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2897. Min Act: -0.0001

Data Index: 613378 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3043. Min Act: -0.0000

Data Index: 623265 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1059345 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2964. Min Act: -0.0000

Data Index: 259020 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3029. Min Act: -0.0001

Data Index: 422526 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2814. Min Act: -0.0001

Data Index: 184249 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1128804 (C4 (Web Text))

Max Activating Token Index: 525