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

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

Neuron 470 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6890. Min Act: -0.0000

Data Index: 114626 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.7476. Min Act: -0.0000

Data Index: 735076 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6411. Min Act: -0.0000

Data Index: 929756 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6510. Min Act: -0.0000

Data Index: 32820 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6013. Min Act: -0.0000

Data Index: 44396 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6348. Min Act: -0.0000

Data Index: 440251 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6860. Min Act: -0.0000

Data Index: 519356 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1053768 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6138. Min Act: -0.0000

Data Index: 731784 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1204451 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6235. Min Act: -0.0000

Data Index: 472699 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1102690 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5936. Min Act: -0.0000

Data Index: 560443 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1338743 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6256. Min Act: -0.0000

Data Index: 496073 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6644. Min Act: -0.0000

Data Index: 528482 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.6141. Min Act: -0.0000

Data Index: 930712 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5921. Min Act: -0.0000

Data Index: 561208 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5997. Min Act: -0.0000

Data Index: 752333 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5787. Min Act: -0.0000

Data Index: 139240 (C4 (Web Text))

Max Activating Token Index: 272