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

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

Neuron 2676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6884. Min Act: -0.0002

Data Index: 1011122 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6352. Min Act: -0.0002

Data Index: 1155895 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5939. Min Act: -0.0001

Data Index: 942662 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5878. Min Act: -0.0002

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6032. Min Act: -0.0001

Data Index: 856672 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6070. Min Act: -0.0001

Data Index: 279784 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5651. Min Act: -0.0001

Data Index: 227605 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5870. Min Act: -0.0002

Data Index: 673556 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6272. Min Act: -0.0002

Data Index: 235111 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5455. Min Act: -0.0002

Data Index: 861694 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5425. Min Act: -0.0002

Data Index: 381599 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5811. Min Act: -0.0001

Data Index: 759044 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5956. Min Act: -0.0002

Data Index: 1339460 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5782. Min Act: -0.0002

Data Index: 1199026 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5397. Min Act: -0.0002

Data Index: 838593 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5593. Min Act: -0.0002

Data Index: 141402 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5360. Min Act: -0.0001

Data Index: 56123 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5657. Min Act: -0.0001

Data Index: 30826 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5702. Min Act: -0.0001

Data Index: 830022 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5482. Min Act: -0.0002

Data Index: 582663 (C4 (Web Text))

Max Activating Token Index: 65