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

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

Neuron 2223 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1152799 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1115606 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.6467. Min Act: -0.0000

Data Index: 100961 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5573. Min Act: -0.0000

Data Index: 359123 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5670. Min Act: 0.0000

Data Index: 1368446 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5730. Min Act: 0.0000

Data Index: 1364758 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5216. Min Act: -0.0000

Data Index: 344614 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5408. Min Act: -0.0000

Data Index: 704353 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5267. Min Act: -0.0000

Data Index: 837178 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4955. Min Act: -0.0000

Data Index: 734281 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4876. Min Act: -0.0000

Data Index: 520407 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4677. Min Act: -0.0000

Data Index: 960778 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1192376 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4978. Min Act: -0.0000

Data Index: 499625 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4406. Min Act: -0.0000

Data Index: 867617 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4541. Min Act: -0.0000

Data Index: 842443 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1308082 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1445609 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4551. Min Act: 0.0000

Data Index: 569310 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4417. Min Act: -0.0000

Data Index: 996483 (C4 (Web Text))

Max Activating Token Index: 422