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

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

Neuron 4619 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5351. Min Act: -0.0001

Data Index: 705416 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5351. Min Act: -0.0001

Data Index: 933050 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1205920 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4672. Min Act: -0.0001

Data Index: 294710 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4215. Min Act: -0.0001

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4814. Min Act: -0.0001

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4750. Min Act: -0.0001

Data Index: 902597 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4697. Min Act: -0.0001

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4685. Min Act: -0.0001

Data Index: 1259665 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1303094 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4752. Min Act: -0.0001

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4548. Min Act: -0.0001

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4628. Min Act: -0.0001

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4589. Min Act: -0.0001

Data Index: 439289 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4381. Min Act: -0.0001

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4515. Min Act: -0.0001

Data Index: 752302 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4431. Min Act: -0.0001

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4299. Min Act: -0.0001

Data Index: 577346 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4333. Min Act: -0.0001

Data Index: 86426 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4543. Min Act: -0.0001

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 638