Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1040 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5289. Min Act: -0.0001

Data Index: 56533 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5583. Min Act: -0.0001

Data Index: 479151 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4377. Min Act: -0.0001

Data Index: 285598 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5357. Min Act: -0.0001

Data Index: 260260 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2835. Min Act: -0.0001

Data Index: 1318893 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4060. Min Act: -0.0001

Data Index: 524502 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.3761. Min Act: -0.0001

Data Index: 1246060 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.3219. Min Act: -0.0001

Data Index: 1269941 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.3694. Min Act: -0.0001

Data Index: 444406 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2832. Min Act: -0.0001

Data Index: 811398 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.3687. Min Act: -0.0001

Data Index: 86664 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.3933. Min Act: -0.0001

Data Index: 65168 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.3253. Min Act: -0.0001

Data Index: 905399 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2956. Min Act: -0.0001

Data Index: 606915 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2640. Min Act: -0.0001

Data Index: 1265922 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2592. Min Act: -0.0001

Data Index: 209195 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.1124. Min Act: -0.0001

Data Index: 838379 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2581. Min Act: -0.0001

Data Index: 905449 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2821. Min Act: -0.0001

Data Index: 1051148 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.2017. Min Act: -0.0001

Data Index: 174214 (C4 (Web Text))

Max Activating Token Index: 1001