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

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

Neuron 3884 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: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1083874 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0555. Min Act: -0.0001

Data Index: 209589 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0552. Min Act: -0.0001

Data Index: 659599 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0543. Min Act: -0.0001

Data Index: 796196 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1047075 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0544. Min Act: -0.0001

Data Index: 564179 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0543. Min Act: -0.0001

Data Index: 45286 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0535. Min Act: -0.0001

Data Index: 643111 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0531. Min Act: -0.0001

Data Index: 138994 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0534. Min Act: -0.0001

Data Index: 834508 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0531. Min Act: -0.0001

Data Index: 772774 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0532. Min Act: -0.0001

Data Index: 478620 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0527. Min Act: -0.0001

Data Index: 300801 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0525. Min Act: -0.0001

Data Index: 52567 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0523. Min Act: -0.0001

Data Index: 849636 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1173377 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1259934 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0520. Min Act: -0.0001

Data Index: 715802 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0001

Data Index: 970218 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1355977 (C4 (Web Text))

Max Activating Token Index: 776