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

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

Neuron 1813 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: 1.6643. Min Range: -1.6643

Max Act: 1.6643. Min Act: -0.0003

Data Index: 226207 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4646. Min Act: -0.0003

Data Index: 73547 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4767. Min Act: -0.0003

Data Index: 694895 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4221. Min Act: -0.0003

Data Index: 537843 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3783. Min Act: -0.0003

Data Index: 809360 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2891. Min Act: -0.0003

Data Index: 931459 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3738. Min Act: -0.0003

Data Index: 511636 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3898. Min Act: -0.0003

Data Index: 12325 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3894. Min Act: -0.0003

Data Index: 501825 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2581. Min Act: -0.0003

Data Index: 806709 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3310. Min Act: -0.0003

Data Index: 1170189 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2865. Min Act: -0.0003

Data Index: 1160791 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3288. Min Act: -0.0003

Data Index: 554626 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3537. Min Act: -0.0003

Data Index: 1309257 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3150. Min Act: -0.0003

Data Index: 233716 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.0736. Min Act: -0.0003

Data Index: 1255859 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2362. Min Act: -0.0003

Data Index: 441984 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2996. Min Act: -0.0003

Data Index: 1028077 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2671. Min Act: -0.0003

Data Index: 700011 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3241. Min Act: -0.0003

Data Index: 718481 (C4 (Web Text))

Max Activating Token Index: 540