Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1940 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0001

Data Index: 658942 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0557. Min Act: -0.0001

Data Index: 459958 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0544. Min Act: -0.0000

Data Index: 452501 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0535. Min Act: -0.0002

Data Index: 166898 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0524. Min Act: -0.0002

Data Index: 757594 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0505. Min Act: -0.0001

Data Index: 260505 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0501. Min Act: -0.0001

Data Index: 46398 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0496. Min Act: -0.0002

Data Index: 696789 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0494. Min Act: -0.0002

Data Index: 430962 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0495. Min Act: -0.0002

Data Index: 807614 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0486. Min Act: -0.0002

Data Index: 338186 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0475. Min Act: -0.0002

Data Index: 871849 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0495. Min Act: -0.0001

Data Index: 109857 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1171077 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1330700 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0482. Min Act: -0.0002

Data Index: 486878 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1168995 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0480. Min Act: -0.0001

Data Index: 729412 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0478. Min Act: -0.0002

Data Index: 431016 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0457. Min Act: -0.0002

Data Index: 231655 (C4 (Web Text))

Max Activating Token Index: 328