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

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

Neuron 4313 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: 3.2411. Min Range: -3.2411

Max Act: 3.2411. Min Act: -0.0000

Data Index: 1126070 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 3.2411. Min Range: -3.2411

Max Act: 3.0658. Min Act: -0.0000

Data Index: 999820 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.2411. Min Range: -3.2411

Max Act: 3.0495. Min Act: -0.0000

Data Index: 42096 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.7585. Min Act: -0.0000

Data Index: 815570 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4619. Min Act: -0.0000

Data Index: 715221 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4856. Min Act: -0.0000

Data Index: 839494 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4866. Min Act: -0.0000

Data Index: 1808 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4751. Min Act: -0.0000

Data Index: 511080 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4571. Min Act: -0.0000

Data Index: 27236 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4495. Min Act: -0.0000

Data Index: 1019964 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.3364. Min Act: -0.0000

Data Index: 1025630 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.4177. Min Act: -0.0000

Data Index: 674295 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.3039. Min Act: -0.0000

Data Index: 22852 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.3932. Min Act: -0.0000

Data Index: 1446548 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.2494. Min Act: -0.0000

Data Index: 980766 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.3544. Min Act: -0.0000

Data Index: 1290155 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.2959. Min Act: -0.0000

Data Index: 676705 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.2828. Min Act: -0.0000

Data Index: 667487 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.3984. Min Act: -0.0000

Data Index: 381677 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 3.2411. Min Range: -3.2411

Max Act: 2.1805. Min Act: -0.0000

Data Index: 411735 (C4 (Web Text))

Max Activating Token Index: 792