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

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

Neuron 3236 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1610843 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1575894 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1436639 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5417. Min Act: -0.0000

Data Index: 255841 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5328. Min Act: -0.0000

Data Index: 166554 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1652520 (Python Code)

Max Activating Token Index: 908

Text #6

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1498469 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1093834 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5069. Min Act: -0.0000

Data Index: 758723 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1451372 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1382205 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4548. Min Act: -0.0000

Data Index: 659950 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4394. Min Act: -0.0000

Data Index: 407642 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4772. Min Act: -0.0000

Data Index: 59759 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1604536 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1021113 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1154539 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4587. Min Act: -0.0000

Data Index: 454120 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1590801 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1209083 (C4 (Web Text))

Max Activating Token Index: 614