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

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

Neuron 3551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3483. Min Act: -0.0000

Data Index: 696581 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3215. Min Act: -0.0000

Data Index: 342504 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1172681 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2764. Min Act: -0.0000

Data Index: 759191 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2787. Min Act: -0.0000

Data Index: 990746 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2577. Min Act: -0.0000

Data Index: 71993 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1350155 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2566. Min Act: -0.0000

Data Index: 264306 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2636. Min Act: -0.0000

Data Index: 525896 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2615. Min Act: -0.0000

Data Index: 851032 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2467. Min Act: -0.0000

Data Index: 896067 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1285729 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1092976 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2599. Min Act: -0.0000

Data Index: 406657 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2463. Min Act: -0.0000

Data Index: 642007 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2832. Min Act: -0.0000

Data Index: 875996 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2422. Min Act: -0.0000

Data Index: 502074 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2448. Min Act: -0.0000

Data Index: 652197 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1642697 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2506. Min Act: -0.0000

Data Index: 222004 (C4 (Web Text))

Max Activating Token Index: 15