Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3595. Min Act: -0.0001

Data Index: 334491 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3294. Min Act: -0.0001

Data Index: 473877 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1033343 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2897. Min Act: -0.0001

Data Index: 770271 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1314938 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2637. Min Act: -0.0001

Data Index: 262382 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2554. Min Act: -0.0001

Data Index: 740311 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2446. Min Act: -0.0001

Data Index: 744417 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1185160 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1023761 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2461. Min Act: -0.0001

Data Index: 458195 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2484. Min Act: -0.0001

Data Index: 365497 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2370. Min Act: -0.0001

Data Index: 970857 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2413. Min Act: -0.0001

Data Index: 596173 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2327. Min Act: -0.0001

Data Index: 949184 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2466. Min Act: -0.0001

Data Index: 498417 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2399. Min Act: -0.0001

Data Index: 265948 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2368. Min Act: -0.0001

Data Index: 37673 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2492. Min Act: -0.0001

Data Index: 246339 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2322. Min Act: -0.0001

Data Index: 489221 (C4 (Web Text))

Max Activating Token Index: 448