Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 356 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.1458. Min Act: -0.0001

Data Index: 987576 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.0816. Min Act: -0.0001

Data Index: 282281 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.0558. Min Act: -0.0001

Data Index: 1086640 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.0024. Min Act: -0.0001

Data Index: 363531 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9938. Min Act: -0.0001

Data Index: 124098 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9853. Min Act: -0.0001

Data Index: 203120 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9090. Min Act: -0.0001

Data Index: 224212 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.0216. Min Act: -0.0001

Data Index: 353283 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9850. Min Act: -0.0001

Data Index: 221072 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9547. Min Act: -0.0001

Data Index: 1078305 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9567. Min Act: -0.0001

Data Index: 1361995 (Python Code)

Max Activating Token Index: 81

Text #11

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.0248. Min Act: -0.0001

Data Index: 153690 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9035. Min Act: -0.0001

Data Index: 157003 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8758. Min Act: -0.0001

Data Index: 405031 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8332. Min Act: -0.0001

Data Index: 1474800 (Python Code)

Max Activating Token Index: 865

Text #15

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8579. Min Act: -0.0001

Data Index: 136652 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8912. Min Act: -0.0001

Data Index: 326871 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8553. Min Act: -0.0001

Data Index: 1212544 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8797. Min Act: -0.0001

Data Index: 535719 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8429. Min Act: -0.0001

Data Index: 538306 (C4 (Web Text))

Max Activating Token Index: 60