Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3883. Min Act: -0.0001

Data Index: 291944 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3749. Min Act: -0.0000

Data Index: 715609 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3287. Min Act: -0.0000

Data Index: 437630 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1438664 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3217. Min Act: 0.0000

Data Index: 1803768 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2992. Min Act: -0.0001

Data Index: 249221 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2703. Min Act: -0.0000

Data Index: 977031 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2793. Min Act: 0.0000

Data Index: 1511690 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2737. Min Act: -0.0001

Data Index: 849312 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1423001 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2609. Min Act: -0.0001

Data Index: 263096 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1735657 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1501225 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2480. Min Act: -0.0000

Data Index: 205973 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2634. Min Act: -0.0000

Data Index: 460471 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1044678 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2491. Min Act: -0.0001

Data Index: 551561 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2479. Min Act: -0.0000

Data Index: 881290 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1223490 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1041773 (The Pile)

Max Activating Token Index: 848