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

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

Neuron 986 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.0532. Min Act: -0.0001

Data Index: 1241153 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.4813. Min Act: -0.0001

Data Index: 1226819 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.7385. Min Act: -0.0000

Data Index: 1271149 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.1241. Min Act: -0.0001

Data Index: 967005 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.9956. Min Act: -0.0001

Data Index: 165578 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.1451. Min Act: -0.0001

Data Index: 135581 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.8452. Min Act: -0.0001

Data Index: 652132 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.1432. Min Act: -0.0001

Data Index: 683043 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.2505. Min Act: -0.0001

Data Index: 376795 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.1385. Min Act: -0.0001

Data Index: 1098837 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.8425. Min Act: -0.0001

Data Index: 129403 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.2872. Min Act: -0.0001

Data Index: 1202919 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.4369. Min Act: -0.0001

Data Index: 815513 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 3.4813. Min Range: -3.4813

Max Act: 3.1739. Min Act: -0.0000

Data Index: 324209 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.8711. Min Act: -0.0001

Data Index: 185460 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.8234. Min Act: -0.0001

Data Index: 437097 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.5545. Min Act: -0.0001

Data Index: 172122 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.8067. Min Act: -0.0000

Data Index: 899208 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.6243. Min Act: -0.0001

Data Index: 28169 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.4813. Min Range: -3.4813

Max Act: 2.6995. Min Act: -0.0001

Data Index: 703171 (C4 (Web Text))

Max Activating Token Index: 378