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

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

Neuron 3600 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: 0.3213. Min Range: -0.3213

Max Act: 0.3213. Min Act: -0.0000

Data Index: 361143 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1098917 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2791. Min Act: -0.0000

Data Index: 272904 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1043019 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2640. Min Act: -0.0001

Data Index: 155008 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2392. Min Act: -0.0000

Data Index: 632659 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2621. Min Act: -0.0000

Data Index: 420955 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2551. Min Act: -0.0001

Data Index: 608833 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2364. Min Act: -0.0001

Data Index: 52028 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2027. Min Act: -0.0001

Data Index: 300170 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2297. Min Act: -0.0001

Data Index: 993090 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1209620 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2342. Min Act: -0.0001

Data Index: 842626 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2227. Min Act: -0.0001

Data Index: 1010616 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2228. Min Act: -0.0000

Data Index: 637501 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2143. Min Act: -0.0000

Data Index: 390448 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2051. Min Act: -0.0000

Data Index: 613014 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2111. Min Act: -0.0001

Data Index: 532285 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2115. Min Act: -0.0000

Data Index: 678589 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2082. Min Act: -0.0001

Data Index: 31676 (C4 (Web Text))

Max Activating Token Index: 503