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

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

Neuron 2139 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1065075 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1096948 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4096. Min Act: -0.0001

Data Index: 435682 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3443. Min Act: -0.0001

Data Index: 35214 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3641. Min Act: -0.0001

Data Index: 1032037 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3982. Min Act: -0.0001

Data Index: 825564 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3464. Min Act: -0.0001

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3717. Min Act: -0.0001

Data Index: 872742 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1163994 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3321. Min Act: -0.0001

Data Index: 980034 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3155. Min Act: -0.0001

Data Index: 737111 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3366. Min Act: -0.0001

Data Index: 556848 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3099. Min Act: -0.0001

Data Index: 91980 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3026. Min Act: -0.0001

Data Index: 540575 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3221. Min Act: -0.0001

Data Index: 371060 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2929. Min Act: -0.0001

Data Index: 796762 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2904. Min Act: -0.0001

Data Index: 1301335 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3220. Min Act: -0.0001

Data Index: 958856 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2942. Min Act: -0.0001

Data Index: 1063102 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1195071 (C4 (Web Text))

Max Activating Token Index: 947