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

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

Neuron 3378 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3839. Min Act: -0.0000

Data Index: 690987 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3368. Min Act: -0.0000

Data Index: 169666 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3570. Min Act: -0.0000

Data Index: 506400 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3247. Min Act: -0.0000

Data Index: 180149 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3213. Min Act: -0.0000

Data Index: 979288 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3160. Min Act: -0.0000

Data Index: 902354 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3005. Min Act: -0.0000

Data Index: 843104 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2982. Min Act: -0.0001

Data Index: 280419 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.3059. Min Act: -0.0001

Data Index: 374863 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2964. Min Act: -0.0001

Data Index: 148735 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2894. Min Act: -0.0001

Data Index: 176527 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2993. Min Act: -0.0000

Data Index: 704464 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2686. Min Act: -0.0000

Data Index: 414179 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2874. Min Act: -0.0000

Data Index: 590050 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1169118 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1098905 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1393645 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2652. Min Act: -0.0001

Data Index: 511260 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2651. Min Act: -0.0001

Data Index: 105759 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.3839. Min Range: -0.3839

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1315442 (C4 (Web Text))

Max Activating Token Index: 773