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

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

Neuron 695 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5842. Min Act: -0.0003

Data Index: 680119 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5551. Min Act: -0.0003

Data Index: 526018 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6706. Min Act: -0.0003

Data Index: 313680 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6485. Min Act: -0.0003

Data Index: 1063368 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5491. Min Act: -0.0003

Data Index: 1049460 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5304. Min Act: -0.0003

Data Index: 71699 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5455. Min Act: -0.0003

Data Index: 1109919 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6569. Min Act: -0.0003

Data Index: 845041 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5663. Min Act: -0.0003

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5990. Min Act: -0.0003

Data Index: 1008124 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4871. Min Act: -0.0003

Data Index: 457254 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4785. Min Act: -0.0003

Data Index: 228114 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5562. Min Act: -0.0003

Data Index: 941617 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.3966. Min Act: -0.0003

Data Index: 1301796 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4105. Min Act: -0.0003

Data Index: 157498 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6048. Min Act: -0.0003

Data Index: 530624 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5464. Min Act: -0.0003

Data Index: 1310374 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5099. Min Act: -0.0003

Data Index: 579300 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5088. Min Act: -0.0003

Data Index: 790284 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5802. Min Act: -0.0003

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 511