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

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

Neuron 1889 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: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0006

Data Index: 376923 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0486. Min Act: -0.0006

Data Index: 860968 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0496. Min Act: -0.0006

Data Index: 361988 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0443. Min Act: -0.0006

Data Index: 633 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0441. Min Act: -0.0006

Data Index: 687818 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0462. Min Act: -0.0006

Data Index: 1335569 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0441. Min Act: -0.0006

Data Index: 422930 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0456. Min Act: -0.0006

Data Index: 627407 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0441. Min Act: -0.0006

Data Index: 266064 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0450. Min Act: -0.0006

Data Index: 896377 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0446. Min Act: -0.0006

Data Index: 1129648 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0444. Min Act: -0.0006

Data Index: 1180902 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0416. Min Act: -0.0006

Data Index: 491343 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0444. Min Act: -0.0006

Data Index: 970827 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0423. Min Act: -0.0006

Data Index: 351192 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0413. Min Act: -0.0006

Data Index: 201293 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0432. Min Act: -0.0006

Data Index: 760781 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0432. Min Act: -0.0006

Data Index: 1098710 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0427. Min Act: -0.0006

Data Index: 701436 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0432. Min Act: -0.0006

Data Index: 343865 (C4 (Web Text))

Max Activating Token Index: 22