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

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

Neuron 1598 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: 1.8632. Min Range: -1.8632

Max Act: 1.8632. Min Act: -0.0001

Data Index: 271568 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.7531. Min Act: -0.0001

Data Index: 588153 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6663. Min Act: -0.0001

Data Index: 588687 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.7283. Min Act: -0.0001

Data Index: 724597 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6873. Min Act: -0.0001

Data Index: 545080 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6406. Min Act: -0.0001

Data Index: 267143 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5759. Min Act: -0.0001

Data Index: 1268935 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6093. Min Act: -0.0001

Data Index: 1222260 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4585. Min Act: -0.0001

Data Index: 750641 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5557. Min Act: -0.0001

Data Index: 743064 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5503. Min Act: -0.0001

Data Index: 623907 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5784. Min Act: -0.0001

Data Index: 860744 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6998. Min Act: -0.0001

Data Index: 348283 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5635. Min Act: -0.0001

Data Index: 92034 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4743. Min Act: -0.0001

Data Index: 871774 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.6441. Min Act: -0.0001

Data Index: 166330 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4737. Min Act: -0.0001

Data Index: 312681 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5862. Min Act: -0.0001

Data Index: 927119 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.5339. Min Act: -0.0001

Data Index: 1039531 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.8632. Min Range: -1.8632

Max Act: 1.4083. Min Act: -0.0001

Data Index: 19200 (C4 (Web Text))

Max Activating Token Index: 650