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

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

Neuron 4594 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1207377 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0512. Min Act: -0.0001

Data Index: 718952 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0502. Min Act: -0.0001

Data Index: 888819 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0508. Min Act: -0.0001

Data Index: 614587 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0499. Min Act: -0.0001

Data Index: 233271 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0497. Min Act: -0.0001

Data Index: 145121 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1127032 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0500. Min Act: -0.0001

Data Index: 674918 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1286986 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0496. Min Act: -0.0001

Data Index: 926128 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1117958 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0493. Min Act: -0.0001

Data Index: 858023 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0478. Min Act: -0.0001

Data Index: 493610 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0489. Min Act: -0.0001

Data Index: 656021 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0493. Min Act: -0.0001

Data Index: 318823 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0493. Min Act: -0.0001

Data Index: 993748 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1165329 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1206523 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1225689 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0481. Min Act: -0.0001

Data Index: 516642 (C4 (Web Text))

Max Activating Token Index: 377