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

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

Neuron 2934 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1613. Min Range: -1.1613

Max Act: 1.1285. Min Act: -0.0001

Data Index: 97188 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 1.1613. Min Range: -1.1613

Max Act: 1.1613. Min Act: -0.0001

Data Index: 119587 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.1613. Min Range: -1.1613

Max Act: 1.0945. Min Act: -0.0001

Data Index: 789014 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.1613. Min Range: -1.1613

Max Act: 1.1076. Min Act: -0.0001

Data Index: 98832 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.1613. Min Range: -1.1613

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1124881 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.9844. Min Act: -0.0001

Data Index: 898613 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.9238. Min Act: -0.0001

Data Index: 776213 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8913. Min Act: -0.0001

Data Index: 340109 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.9253. Min Act: -0.0001

Data Index: 278111 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8646. Min Act: -0.0001

Data Index: 1220475 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8792. Min Act: -0.0001

Data Index: 171175 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7725. Min Act: -0.0001

Data Index: 1191992 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8875. Min Act: -0.0001

Data Index: 183444 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.9043. Min Act: -0.0001

Data Index: 442342 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8680. Min Act: -0.0001

Data Index: 153320 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7891. Min Act: -0.0001

Data Index: 616495 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8410. Min Act: -0.0001

Data Index: 124294 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8374. Min Act: -0.0001

Data Index: 634039 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8221. Min Act: -0.0001

Data Index: 692405 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7946. Min Act: -0.0001

Data Index: 256319 (C4 (Web Text))

Max Activating Token Index: 86