Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2460 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.6016. Min Act: -0.0003

Data Index: 247017 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.5500. Min Act: -0.0003

Data Index: 841623 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3653. Min Act: -0.0003

Data Index: 517360 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3360. Min Act: -0.0003

Data Index: 746795 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.4454. Min Act: -0.0003

Data Index: 790924 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3402. Min Act: -0.0003

Data Index: 1067137 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3296. Min Act: -0.0003

Data Index: 802444 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.4126. Min Act: -0.0003

Data Index: 273962 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2709. Min Act: -0.0003

Data Index: 576098 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3054. Min Act: -0.0003

Data Index: 1242434 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3433. Min Act: -0.0003

Data Index: 42332 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2460. Min Act: -0.0003

Data Index: 1354203 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2295. Min Act: -0.0003

Data Index: 1298579 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1603. Min Act: -0.0003

Data Index: 1020946 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2591. Min Act: -0.0003

Data Index: 535888 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2976. Min Act: -0.0003

Data Index: 34424 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2371. Min Act: -0.0003

Data Index: 959000 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3649. Min Act: -0.0003

Data Index: 559224 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1691. Min Act: -0.0003

Data Index: 628122 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3138. Min Act: -0.0003

Data Index: 1359506 (C4 (Web Text))

Max Activating Token Index: 922