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

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

Neuron 141 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: 0.0548. Min Range: -0.0548

Max Act: 0.0492. Min Act: -0.0006

Data Index: 365300 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0541. Min Act: -0.0006

Data Index: 312289 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0520. Min Act: -0.0006

Data Index: 526661 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0481. Min Act: -0.0006

Data Index: 749113 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0503. Min Act: -0.0006

Data Index: 382047 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0006

Data Index: 883488 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0495. Min Act: -0.0006

Data Index: 478443 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0519. Min Act: -0.0006

Data Index: 124237 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0432. Min Act: -0.0006

Data Index: 527861 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0470. Min Act: -0.0006

Data Index: 212727 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0477. Min Act: -0.0006

Data Index: 581983 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0485. Min Act: -0.0006

Data Index: 795714 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1141123 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0495. Min Act: -0.0006

Data Index: 351144 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1138793 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0483. Min Act: -0.0006

Data Index: 1156169 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0503. Min Act: -0.0006

Data Index: 364802 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0479. Min Act: -0.0006

Data Index: 669 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0477. Min Act: -0.0006

Data Index: 370036 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1139515 (C4 (Web Text))

Max Activating Token Index: 43