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

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

Neuron 5731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1380. Min Range: -2.1380

Max Act: 2.1380. Min Act: -0.0000

Data Index: 595852 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.8694. Min Act: -0.0000

Data Index: 949256 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.7655. Min Act: -0.0000

Data Index: 1296747 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.7741. Min Act: -0.0000

Data Index: 679117 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.6702. Min Act: -0.0000

Data Index: 249036 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.6232. Min Act: -0.0000

Data Index: 145603 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.6096. Min Act: -0.0000

Data Index: 690670 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.6749. Min Act: -0.0000

Data Index: 1340792 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.4697. Min Act: -0.0000

Data Index: 35091 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.3489. Min Act: -0.0000

Data Index: 534968 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1121890 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.4426. Min Act: -0.0000

Data Index: 897555 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1078231 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.3291. Min Act: -0.0000

Data Index: 258478 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.2926. Min Act: -0.0000

Data Index: 896755 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.3079. Min Act: -0.0000

Data Index: 660105 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.3462. Min Act: -0.0000

Data Index: 320960 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.1566. Min Act: -0.0000

Data Index: 1219749 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.1784. Min Act: -0.0000

Data Index: 585117 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 2.1380. Min Range: -2.1380

Max Act: 1.2479. Min Act: -0.0000

Data Index: 21127 (C4 (Web Text))

Max Activating Token Index: 213