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

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

Neuron 4921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1086525 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.2065. Min Act: -0.0001

Data Index: 143724 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0503. Min Act: -0.0001

Data Index: 769248 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0461. Min Act: -0.0001

Data Index: 1284544 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.1438. Min Act: -0.0001

Data Index: 992795 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0696. Min Act: -0.0001

Data Index: 1152181 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.9613. Min Act: -0.0001

Data Index: 466162 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.1179. Min Act: -0.0001

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0557. Min Act: -0.0001

Data Index: 239745 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.9814. Min Act: -0.0001

Data Index: 325841 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1645573 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0559. Min Act: -0.0001

Data Index: 615604 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1650632 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0313. Min Act: -0.0001

Data Index: 617828 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.9565. Min Act: -0.0001

Data Index: 430963 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0283. Min Act: -0.0001

Data Index: 1509117 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0327. Min Act: -0.0001

Data Index: 1414629 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1120376 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.0296. Min Act: -0.0001

Data Index: 1331687 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.9992. Min Act: -0.0001

Data Index: 1577208 (Python Code)

Max Activating Token Index: 128