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

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

Neuron 1212 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: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1527454 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1611366 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0516. Min Act: -0.0002

Data Index: 603531 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0500. Min Act: -0.0002

Data Index: 663508 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1155344 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1044276 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0500. Min Act: -0.0002

Data Index: 575675 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1230208 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0489. Min Act: -0.0002

Data Index: 210161 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1271603 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1216376 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0464. Min Act: -0.0002

Data Index: 895770 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0474. Min Act: -0.0002

Data Index: 813046 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1424558 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0468. Min Act: -0.0002

Data Index: 471149 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1496781 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0450. Min Act: -0.0002

Data Index: 813052 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1166409 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1457588 (Python Code)

Max Activating Token Index: 251

Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0454. Min Act: -0.0001

Data Index: 72368 (C4 (Web Text))

Max Activating Token Index: 602