Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 337 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4972. Min Act: -0.0000

Data Index: 148245 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1316939 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4528. Min Act: -0.0001

Data Index: 660557 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4399. Min Act: -0.0000

Data Index: 132395 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4241. Min Act: -0.0000

Data Index: 993145 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4326. Min Act: -0.0000

Data Index: 846472 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3913. Min Act: -0.0000

Data Index: 531135 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3526. Min Act: -0.0001

Data Index: 803712 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3911. Min Act: -0.0000

Data Index: 424131 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3597. Min Act: -0.0000

Data Index: 435855 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3785. Min Act: -0.0000

Data Index: 249551 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3916. Min Act: -0.0001

Data Index: 170570 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3629. Min Act: -0.0000

Data Index: 704169 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1196405 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1349584 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3897. Min Act: -0.0000

Data Index: 329193 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3652. Min Act: -0.0001

Data Index: 860213 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3599. Min Act: -0.0000

Data Index: 852732 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3613. Min Act: -0.0000

Data Index: 227399 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3583. Min Act: -0.0000

Data Index: 764250 (C4 (Web Text))

Max Activating Token Index: 958