Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6943. Min Act: -0.0000

Data Index: 519027 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6736. Min Act: -0.0000

Data Index: 789512 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6685. Min Act: -0.0000

Data Index: 546895 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.4748. Min Act: -0.0000

Data Index: 472672 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6566. Min Act: -0.0000

Data Index: 466685 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6501. Min Act: -0.0000

Data Index: 1215783 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6722. Min Act: -0.0000

Data Index: 912982 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6348. Min Act: -0.0000

Data Index: 82213 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6375. Min Act: -0.0000

Data Index: 1102886 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.8231. Min Act: -0.0000

Data Index: 1277555 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.3703. Min Act: -0.0000

Data Index: 853268 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.5370. Min Act: -0.0000

Data Index: 1048011 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6940. Min Act: -0.0000

Data Index: 1219708 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.5046. Min Act: -0.0000

Data Index: 500960 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.4859. Min Act: -0.0000

Data Index: 546887 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.3042. Min Act: -0.0000

Data Index: 500476 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.2843. Min Act: -0.0000

Data Index: 91209 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6218. Min Act: -0.0000

Data Index: 225270 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.2405. Min Act: -0.0000

Data Index: 107990 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 6.8231. Min Range: -6.8231

Max Act: 6.6077. Min Act: -0.0000

Data Index: 516414 (C4 (Web Text))

Max Activating Token Index: 984