Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4132. Min Range: -2.4132

Max Act: 2.4132. Min Act: -0.0000

Data Index: 653531 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.4132. Min Range: -2.4132

Max Act: 2.1371. Min Act: -0.0000

Data Index: 793358 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.9771. Min Act: -0.0000

Data Index: 790981 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.9881. Min Act: -0.0000

Data Index: 961491 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.9270. Min Act: -0.0000

Data Index: 337756 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.7964. Min Act: -0.0000

Data Index: 873257 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1209442 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.7748. Min Act: -0.0000

Data Index: 696019 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.7270. Min Act: -0.0000

Data Index: 520607 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.6055. Min Act: -0.0000

Data Index: 902929 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5730. Min Act: -0.0000

Data Index: 783371 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5517. Min Act: -0.0000

Data Index: 3030 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1153736 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5936. Min Act: -0.0000

Data Index: 775044 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.6701. Min Act: -0.0000

Data Index: 854186 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5393. Min Act: -0.0000

Data Index: 193141 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5054. Min Act: -0.0000

Data Index: 931416 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.5082. Min Act: -0.0000

Data Index: 873057 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.4138. Min Act: -0.0000

Data Index: 212970 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 2.4132. Min Range: -2.4132

Max Act: 1.3781. Min Act: -0.0000

Data Index: 244564 (C4 (Web Text))

Max Activating Token Index: 939