Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3805 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3492. Min Range: -3.3492

Max Act: 3.2565. Min Act: -0.0001

Data Index: 1049043 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.3492. Min Range: -3.3492

Max Act: 3.3492. Min Act: -0.0001

Data Index: 817772 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.8623. Min Act: -0.0000

Data Index: 884191 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.6341. Min Act: -0.0001

Data Index: 1096361 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.6146. Min Act: -0.0000

Data Index: 798547 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.5347. Min Act: -0.0000

Data Index: 1015574 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.4788. Min Act: -0.0000

Data Index: 330725 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.3934. Min Act: -0.0000

Data Index: 8059 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.3230. Min Act: -0.0001

Data Index: 1550028 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.4044. Min Act: -0.0000

Data Index: 786448 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.0721. Min Act: -0.0000

Data Index: 707840 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.2379. Min Act: -0.0001

Data Index: 81239 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.3669. Min Act: -0.0000

Data Index: 139059 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.3862. Min Act: -0.0000

Data Index: 433498 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.0842. Min Act: -0.0001

Data Index: 100278 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 3.3492. Min Range: -3.3492

Max Act: 1.8736. Min Act: -0.0000

Data Index: 719270 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.5700. Min Act: -0.0000

Data Index: 279377 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.2060. Min Act: -0.0001

Data Index: 64791 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.2999. Min Act: -0.0000

Data Index: 1314380 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 3.3492. Min Range: -3.3492

Max Act: 2.1192. Min Act: -0.0000

Data Index: 648836 (C4 (Web Text))

Max Activating Token Index: 342