Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2774 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0001

Data Index: 972899 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0774. Min Act: -0.0000

Data Index: 228797 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0727. Min Act: -0.0000

Data Index: 221248 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1224024 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0631. Min Act: -0.0001

Data Index: 617606 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0670. Min Act: -0.0000

Data Index: 333338 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0613. Min Act: -0.0001

Data Index: 281918 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1246745 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1282620 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1354800 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0559. Min Act: -0.0001

Data Index: 677190 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0566. Min Act: -0.0001

Data Index: 784480 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0538. Min Act: -0.0000

Data Index: 617572 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0527. Min Act: -0.0001

Data Index: 81871 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0501. Min Act: -0.0000

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0583. Min Act: -0.0001

Data Index: 113773 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1143103 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0503. Min Act: -0.0001

Data Index: 790026 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0457. Min Act: -0.0000

Data Index: 803633 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0473. Min Act: -0.0001

Data Index: 992516 (C4 (Web Text))

Max Activating Token Index: 465