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

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

Neuron 250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.9026. Min Act: -0.0001

Data Index: 917413 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7954. Min Act: -0.0001

Data Index: 432661 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7763. Min Act: -0.0001

Data Index: 44464 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7662. Min Act: -0.0001

Data Index: 1591871 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7386. Min Act: -0.0001

Data Index: 213776 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7504. Min Act: -0.0000

Data Index: 279902 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7342. Min Act: -0.0001

Data Index: 1527625 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7825. Min Act: -0.0001

Data Index: 554654 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7542. Min Act: -0.0001

Data Index: 1467416 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7314. Min Act: -0.0000

Data Index: 729671 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1182364 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7325. Min Act: -0.0001

Data Index: 687942 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6866. Min Act: -0.0001

Data Index: 261223 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1269749 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7314. Min Act: -0.0000

Data Index: 39017 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7011. Min Act: -0.0001

Data Index: 445962 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6747. Min Act: -0.0001

Data Index: 566275 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1096399 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6904. Min Act: -0.0000

Data Index: 590131 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6913. Min Act: -0.0001

Data Index: 22952 (C4 (Web Text))

Max Activating Token Index: 503