Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3960. Min Act: -0.0000

Data Index: 586737 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3800. Min Act: -0.0000

Data Index: 95733 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1194773 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3821. Min Act: -0.0000

Data Index: 385178 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3664. Min Act: -0.0000

Data Index: 90678 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1002333 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3705. Min Act: -0.0000

Data Index: 217314 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3439. Min Act: -0.0000

Data Index: 106398 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3172. Min Act: -0.0000

Data Index: 427111 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3287. Min Act: -0.0000

Data Index: 660745 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3610. Min Act: -0.0000

Data Index: 579508 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3346. Min Act: -0.0000

Data Index: 682198 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3369. Min Act: -0.0000

Data Index: 376215 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3364. Min Act: -0.0000

Data Index: 207078 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3343. Min Act: -0.0000

Data Index: 610709 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3272. Min Act: -0.0000

Data Index: 910719 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3474. Min Act: -0.0000

Data Index: 368622 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3261. Min Act: -0.0000

Data Index: 137200 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1079122 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1346531 (C4 (Web Text))

Max Activating Token Index: 899