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

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

Neuron 1996 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: 2.9823. Min Range: -2.9823

Max Act: 2.9823. Min Act: -0.0000

Data Index: 523711 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.7054. Min Act: -0.0000

Data Index: 382397 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.5967. Min Act: -0.0000

Data Index: 1273556 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.6848. Min Act: -0.0000

Data Index: 1108706 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.6782. Min Act: -0.0000

Data Index: 599503 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.4010. Min Act: -0.0000

Data Index: 65428 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.2480. Min Act: -0.0000

Data Index: 874579 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.4550. Min Act: -0.0000

Data Index: 548528 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.4166. Min Act: -0.0000

Data Index: 1292700 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.3867. Min Act: -0.0000

Data Index: 537881 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.3976. Min Act: -0.0001

Data Index: 998238 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.7600. Min Act: -0.0000

Data Index: 1317788 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.2439. Min Act: -0.0001

Data Index: 983429 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.6112. Min Act: -0.0001

Data Index: 888481 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.3549. Min Act: -0.0000

Data Index: 387909 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.3332. Min Act: -0.0000

Data Index: 779452 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.2388. Min Act: -0.0000

Data Index: 1210868 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.4492. Min Act: -0.0000

Data Index: 278098 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.2058. Min Act: -0.0000

Data Index: 1088334 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 2.9823. Min Range: -2.9823

Max Act: 2.2754. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 263