Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3532 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1493599 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0500. Min Act: -0.0001

Data Index: 279881 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1334400 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0485. Min Act: -0.0001

Data Index: 477779 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1152815 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0480. Min Act: -0.0001

Data Index: 817514 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0466. Min Act: -0.0001

Data Index: 6740 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0486. Min Act: -0.0001

Data Index: 94637 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1306 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0484. Min Act: -0.0001

Data Index: 820724 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0479. Min Act: -0.0001

Data Index: 80064 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1202354 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0476. Min Act: -0.0001

Data Index: 562362 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1519574 (Python Code)

Max Activating Token Index: 456

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0465. Min Act: -0.0001

Data Index: 176798 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0463. Min Act: -0.0001

Data Index: 596718 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1394665 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1262031 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0465. Min Act: -0.0001

Data Index: 763229 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1244316 (C4 (Web Text))

Max Activating Token Index: 904