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

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

Neuron 4038 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.8157. Min Act: -0.0000

Data Index: 981867 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.8412. Min Act: -0.0000

Data Index: 875084 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.8698. Min Act: -0.0000

Data Index: 812670 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7616. Min Act: -0.0000

Data Index: 430979 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6576. Min Act: -0.0000

Data Index: 860287 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7520. Min Act: -0.0000

Data Index: 73840 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7717. Min Act: -0.0000

Data Index: 530370 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1280202 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6987. Min Act: -0.0000

Data Index: 606503 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7166. Min Act: -0.0000

Data Index: 450059 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7384. Min Act: -0.0000

Data Index: 564443 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1171889 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1256632 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6879. Min Act: -0.0000

Data Index: 109529 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6825. Min Act: -0.0000

Data Index: 540456 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7543. Min Act: -0.0000

Data Index: 249794 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.7072. Min Act: -0.0000

Data Index: 188763 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6530. Min Act: -0.0000

Data Index: 56443 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6686. Min Act: -0.0000

Data Index: 171036 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.8698. Min Range: -0.8698

Max Act: 0.6565. Min Act: -0.0000

Data Index: 850551 (C4 (Web Text))

Max Activating Token Index: 860