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

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

Neuron 235 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0650. Min Range: -2.0650

Max Act: 2.0650. Min Act: -0.0000

Data Index: 834499 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.9983. Min Act: -0.0000

Data Index: 599374 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.9599. Min Act: -0.0000

Data Index: 677471 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.9004. Min Act: -0.0000

Data Index: 1142297 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.0650. Min Range: -2.0650

Max Act: 2.0008. Min Act: -0.0000

Data Index: 874162 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.8092. Min Act: -0.0000

Data Index: 945744 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.7466. Min Act: -0.0000

Data Index: 734861 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.6213. Min Act: -0.0000

Data Index: 899049 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.6469. Min Act: -0.0000

Data Index: 130362 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.6307. Min Act: -0.0000

Data Index: 88544 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.6458. Min Act: -0.0000

Data Index: 422933 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.6291. Min Act: -0.0000

Data Index: 1145393 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.6220. Min Act: -0.0000

Data Index: 495327 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.4444. Min Act: -0.0000

Data Index: 669396 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.2838. Min Act: -0.0000

Data Index: 30064 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.3773. Min Act: -0.0000

Data Index: 822780 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.2987. Min Act: 0.0000

Data Index: 2182 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.3246. Min Act: -0.0000

Data Index: 301445 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1095860 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 2.0650. Min Range: -2.0650

Max Act: 1.2380. Min Act: -0.0000

Data Index: 198751 (C4 (Web Text))

Max Activating Token Index: 500