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

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

Neuron 3572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.8796. Min Act: -0.0000

Data Index: 665928 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.1289. Min Act: -0.0000

Data Index: 242724 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 3.8796. Min Range: -3.8796

Max Act: 3.1277. Min Act: -0.0000

Data Index: 759507 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.8324. Min Act: -0.0000

Data Index: 429742 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.8085. Min Act: -0.0000

Data Index: 1113268 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.7860. Min Act: -0.0000

Data Index: 1477765 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.7575. Min Act: -0.0000

Data Index: 899322 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.6343. Min Act: -0.0000

Data Index: 274207 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.7436. Min Act: -0.0000

Data Index: 976083 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.7211. Min Act: -0.0000

Data Index: 1156687 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.6953. Min Act: -0.0000

Data Index: 661231 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.6717. Min Act: -0.0000

Data Index: 782504 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.4522. Min Act: -0.0000

Data Index: 558640 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.5491. Min Act: -0.0000

Data Index: 868196 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.5699. Min Act: -0.0000

Data Index: 1454515 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.5276. Min Act: -0.0000

Data Index: 36321 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.2354. Min Act: -0.0000

Data Index: 1649354 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.6395. Min Act: -0.0000

Data Index: 101111 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.4921. Min Act: -0.0000

Data Index: 1344242 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 3.8796. Min Range: -3.8796

Max Act: 2.3602. Min Act: -0.0000

Data Index: 396376 (C4 (Web Text))

Max Activating Token Index: 564