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

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

Neuron 1614 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0526. Min Act: -0.0006

Data Index: 351762 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0506. Min Act: -0.0006

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0006

Data Index: 386784 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0514. Min Act: -0.0006

Data Index: 1133621 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0510. Min Act: -0.0006

Data Index: 199370 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0503. Min Act: -0.0006

Data Index: 811201 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0504. Min Act: -0.0006

Data Index: 496785 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1046257 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0500. Min Act: -0.0006

Data Index: 556943 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0474. Min Act: -0.0006

Data Index: 955728 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0480. Min Act: -0.0006

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1207887 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0472. Min Act: -0.0006

Data Index: 635486 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0460. Min Act: -0.0006

Data Index: 1145324 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0469. Min Act: -0.0006

Data Index: 391033 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0490. Min Act: -0.0006

Data Index: 826185 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0460. Min Act: -0.0006

Data Index: 812437 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0488. Min Act: -0.0006

Data Index: 1119183 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0466. Min Act: -0.0006

Data Index: 702775 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1341407 (C4 (Web Text))

Max Activating Token Index: 612