Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2593. Min Range: -3.2593

Max Act: 3.2593. Min Act: -0.0000

Data Index: 830900 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 3.2593. Min Range: -3.2593

Max Act: 3.1369. Min Act: -0.0000

Data Index: 1349211 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.8367. Min Act: -0.0000

Data Index: 887747 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 3.2593. Min Range: -3.2593

Max Act: 3.0678. Min Act: -0.0000

Data Index: 1049809 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.9175. Min Act: -0.0000

Data Index: 586147 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 3.2593. Min Range: -3.2593

Max Act: 3.0469. Min Act: -0.0000

Data Index: 26480 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.8915. Min Act: -0.0000

Data Index: 833965 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.8544. Min Act: -0.0000

Data Index: 810982 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.7117. Min Act: -0.0000

Data Index: 563343 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.4027. Min Act: -0.0000

Data Index: 1067301 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.5940. Min Act: -0.0000

Data Index: 1158313 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.8319. Min Act: -0.0000

Data Index: 84368 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.6643. Min Act: -0.0000

Data Index: 476478 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.5455. Min Act: -0.0000

Data Index: 407682 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.4443. Min Act: -0.0000

Data Index: 670604 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.3198. Min Act: -0.0000

Data Index: 612465 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.4986. Min Act: -0.0000

Data Index: 811938 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.4562. Min Act: -0.0000

Data Index: 822773 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.4330. Min Act: -0.0000

Data Index: 190108 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 3.2593. Min Range: -3.2593

Max Act: 2.4371. Min Act: -0.0000

Data Index: 1238949 (C4 (Web Text))

Max Activating Token Index: 214