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

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

Neuron 623 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: 0.4373. Min Range: -0.4373

Max Act: 0.4300. Min Act: -0.0001

Data Index: 254256 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4373. Min Act: -0.0001

Data Index: 328431 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3946. Min Act: -0.0001

Data Index: 938201 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3812. Min Act: -0.0001

Data Index: 1021850 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3792. Min Act: -0.0001

Data Index: 580103 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3396. Min Act: -0.0001

Data Index: 999797 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3358. Min Act: -0.0001

Data Index: 1036614 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3129. Min Act: -0.0001

Data Index: 738500 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3110. Min Act: -0.0001

Data Index: 354639 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3229. Min Act: -0.0001

Data Index: 650920 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2965. Min Act: -0.0001

Data Index: 531466 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1047421 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2811. Min Act: -0.0001

Data Index: 767769 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.1977. Min Act: -0.0001

Data Index: 326954 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2520. Min Act: -0.0001

Data Index: 598042 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2642. Min Act: -0.0001

Data Index: 260741 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1139685 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2609. Min Act: -0.0001

Data Index: 949067 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2735. Min Act: -0.0001

Data Index: 253104 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2680. Min Act: -0.0001

Data Index: 492338 (C4 (Web Text))

Max Activating Token Index: 750