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

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

Neuron 2632 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.3562. Min Act: -0.0001

Data Index: 367726 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.3910. Min Act: -0.0001

Data Index: 741165 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.4277. Min Act: -0.0001

Data Index: 121578 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0738. Min Act: -0.0001

Data Index: 1208906 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0695. Min Act: -0.0001

Data Index: 781542 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1588. Min Act: -0.0001

Data Index: 55985 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1092223 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1727. Min Act: -0.0001

Data Index: 563341 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0804. Min Act: -0.0001

Data Index: 660080 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0498. Min Act: -0.0001

Data Index: 685350 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0785. Min Act: -0.0001

Data Index: 352651 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1607. Min Act: -0.0001

Data Index: 363455 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.2082. Min Act: -0.0001

Data Index: 15580 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0036. Min Act: -0.0001

Data Index: 78582 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0410. Min Act: -0.0001

Data Index: 603741 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.4277. Min Range: -1.4277

Max Act: 0.9547. Min Act: -0.0001

Data Index: 462870 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0983. Min Act: -0.0001

Data Index: 402934 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1186. Min Act: -0.0001

Data Index: 1174093 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.4277. Min Range: -1.4277

Max Act: 0.8193. Min Act: -0.0001

Data Index: 1533424 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0294. Min Act: -0.0001

Data Index: 841225 (C4 (Web Text))

Max Activating Token Index: 527