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

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

Neuron 3815 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: 0.3588. Min Range: -0.3588

Max Act: 0.3569. Min Act: -0.0001

Data Index: 849750 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1061568 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3549. Min Act: -0.0001

Data Index: 583001 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3588. Min Act: -0.0001

Data Index: 541743 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3493. Min Act: -0.0001

Data Index: 584826 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3556. Min Act: -0.0001

Data Index: 518589 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3461. Min Act: -0.0001

Data Index: 114676 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3533. Min Act: -0.0001

Data Index: 692454 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3473. Min Act: -0.0001

Data Index: 514713 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3442. Min Act: -0.0002

Data Index: 1113866 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3466. Min Act: -0.0002

Data Index: 508361 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3419. Min Act: -0.0002

Data Index: 816567 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3440. Min Act: -0.0002

Data Index: 862616 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3507. Min Act: -0.0002

Data Index: 159687 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3481. Min Act: -0.0002

Data Index: 621313 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3390. Min Act: -0.0001

Data Index: 118138 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3430. Min Act: -0.0002

Data Index: 235440 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3380. Min Act: -0.0001

Data Index: 504165 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3413. Min Act: -0.0001

Data Index: 684859 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3425. Min Act: -0.0001

Data Index: 331670 (C4 (Web Text))

Max Activating Token Index: 756