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

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

Neuron 4911 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.4968. Min Act: -0.0000

Data Index: 1592316 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.2254. Min Act: -0.0000

Data Index: 1391253 (Python Code)

Max Activating Token Index: 981

Text #2

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.3322. Min Act: -0.0000

Data Index: 955488 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.2558. Min Act: -0.0000

Data Index: 1511128 (Python Code)

Max Activating Token Index: 694

Text #4

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.1962. Min Act: -0.0000

Data Index: 1574228 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.1628. Min Act: -0.0000

Data Index: 570138 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.1606. Min Act: -0.0000

Data Index: 1142923 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.1502. Min Act: -0.0000

Data Index: 1094589 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.4059. Min Act: -0.0000

Data Index: 1420849 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.8983. Min Act: -0.0000

Data Index: 1536006 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.7466. Min Act: -0.0000

Data Index: 842567 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.8305. Min Act: -0.0000

Data Index: 608931 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.8248. Min Act: -0.0000

Data Index: 1414872 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.8150. Min Act: -0.0000

Data Index: 1477765 (Python Code)

Max Activating Token Index: 480

Text #14

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.6790. Min Act: -0.0000

Data Index: 419870 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.4968. Min Range: -3.4968

Max Act: 3.0087. Min Act: -0.0000

Data Index: 1398166 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.7657. Min Act: -0.0000

Data Index: 1370179 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1047351 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.7285. Min Act: -0.0000

Data Index: 1454515 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 3.4968. Min Range: -3.4968

Max Act: 2.7905. Min Act: -0.0000

Data Index: 911804 (C4 (Web Text))

Max Activating Token Index: 303