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

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

Neuron 150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0003

Data Index: 296645 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0585. Min Act: -0.0003

Data Index: 313286 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0570. Min Act: -0.0003

Data Index: 259848 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0577. Min Act: -0.0003

Data Index: 419497 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0553. Min Act: -0.0003

Data Index: 520928 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0535. Min Act: -0.0003

Data Index: 604141 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0501. Min Act: -0.0003

Data Index: 591309 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0466. Min Act: -0.0003

Data Index: 51828 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1297498 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1185810 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1495444 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1345436 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0500. Min Act: -0.0003

Data Index: 250171 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0457. Min Act: -0.0003

Data Index: 392199 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0477. Min Act: -0.0003

Data Index: 460087 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1064283 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0485. Min Act: -0.0003

Data Index: 225560 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0491. Min Act: -0.0003

Data Index: 323579 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0491. Min Act: -0.0003

Data Index: 585136 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1612398 (Python Code)

Max Activating Token Index: 918