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

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

Neuron 1610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.4767. Min Act: -0.0000

Data Index: 863824 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 7.4767. Min Range: -7.4767

Max Act: 7.2147. Min Act: -0.0000

Data Index: 679213 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.4413. Min Act: -0.0000

Data Index: 149393 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.9212. Min Act: -0.0000

Data Index: 1086955 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.4607. Min Act: -0.0000

Data Index: 819319 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.5117. Min Act: -0.0000

Data Index: 272723 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.1791. Min Act: -0.0000

Data Index: 108328 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.2105. Min Act: -0.0000

Data Index: 244768 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.0052. Min Act: -0.0000

Data Index: 1135555 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.8221. Min Act: -0.0000

Data Index: 1310242 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 7.4767. Min Range: -7.4767

Max Act: 6.0605. Min Act: -0.0000

Data Index: 209487 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.9567. Min Act: -0.0000

Data Index: 1177676 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.6711. Min Act: -0.0000

Data Index: 655531 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.6964. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.4851. Min Act: -0.0000

Data Index: 571825 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.3781. Min Act: -0.0000

Data Index: 338035 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.5348. Min Act: -0.0000

Data Index: 1000477 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.1589. Min Act: -0.0000

Data Index: 68428 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.1187. Min Act: -0.0000

Data Index: 564577 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 7.4767. Min Range: -7.4767

Max Act: 5.1053. Min Act: -0.0000

Data Index: 65561 (C4 (Web Text))

Max Activating Token Index: 670