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

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

Neuron 934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0004

Data Index: 414326 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0574. Min Act: -0.0004

Data Index: 777009 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0573. Min Act: -0.0004

Data Index: 1115983 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0549. Min Act: -0.0004

Data Index: 871885 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0543. Min Act: -0.0004

Data Index: 302382 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0463. Min Act: -0.0004

Data Index: 1173763 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0448. Min Act: -0.0004

Data Index: 500004 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0535. Min Act: -0.0004

Data Index: 495031 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0532. Min Act: -0.0004

Data Index: 931938 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0482. Min Act: -0.0004

Data Index: 30006 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0485. Min Act: -0.0004

Data Index: 115608 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0520. Min Act: -0.0004

Data Index: 1393959 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0519. Min Act: -0.0004

Data Index: 996756 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0499. Min Act: -0.0004

Data Index: 1655652 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0518. Min Act: -0.0004

Data Index: 1311220 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0511. Min Act: -0.0004

Data Index: 400759 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0428. Min Act: -0.0004

Data Index: 171316 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0461. Min Act: -0.0004

Data Index: 650297 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0475. Min Act: -0.0004

Data Index: 1591614 (Python Code)

Max Activating Token Index: 389

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0504. Min Act: -0.0004

Data Index: 471312 (C4 (Web Text))

Max Activating Token Index: 407