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

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

Neuron 1550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1493434 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0001

Data Index: 554040 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0360. Min Act: -0.0001

Data Index: 423495 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0381. Min Act: -0.0001

Data Index: 353321 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1537162 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0353. Min Act: -0.0001

Data Index: 509084 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0325. Min Act: -0.0001

Data Index: 277442 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0339. Min Act: -0.0001

Data Index: 752242 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1310125 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0329. Min Act: -0.0001

Data Index: 550949 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0279. Min Act: -0.0001

Data Index: 272626 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0320. Min Act: -0.0001

Data Index: 851575 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0303. Min Act: -0.0001

Data Index: 150938 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0324. Min Act: -0.0001

Data Index: 878485 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0320. Min Act: -0.0001

Data Index: 74408 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1639228 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1621285 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1411473 (Python Code)

Max Activating Token Index: 380

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0316. Min Act: -0.0001

Data Index: 145292 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1116664 (C4 (Web Text))

Max Activating Token Index: 484