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

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

Neuron 2761 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: 1.2944. Min Range: -1.2944

Max Act: 1.2944. Min Act: -0.0001

Data Index: 452604 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2287. Min Act: -0.0001

Data Index: 491922 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9849. Min Act: -0.0001

Data Index: 31206 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9218. Min Act: -0.0001

Data Index: 589907 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9361. Min Act: -0.0001

Data Index: 371485 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0332. Min Act: -0.0001

Data Index: 1136767 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9589. Min Act: -0.0001

Data Index: 127109 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8990. Min Act: -0.0001

Data Index: 1230742 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.7455. Min Act: -0.0001

Data Index: 117231 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8317. Min Act: -0.0001

Data Index: 437021 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.7660. Min Act: -0.0001

Data Index: 309907 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.7888. Min Act: -0.0001

Data Index: 284302 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8452. Min Act: -0.0001

Data Index: 280494 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0183. Min Act: -0.0001

Data Index: 485781 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8317. Min Act: -0.0001

Data Index: 848000 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.6572. Min Act: -0.0001

Data Index: 1001871 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9277. Min Act: -0.0001

Data Index: 756521 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8341. Min Act: -0.0001

Data Index: 863313 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8036. Min Act: -0.0001

Data Index: 920523 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9844. Min Act: -0.0001

Data Index: 991844 (C4 (Web Text))

Max Activating Token Index: 280