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

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

Neuron 4045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1700. Min Act: -0.0000

Data Index: 77678 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.8287. Min Act: -0.0001

Data Index: 201418 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4589. Min Act: -0.0000

Data Index: 655902 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.8189. Min Act: -0.0000

Data Index: 128574 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4268. Min Act: -0.0001

Data Index: 981995 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.7680. Min Act: -0.0000

Data Index: 321072 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.3826. Min Act: -0.0001

Data Index: 906916 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.3370. Min Act: -0.0000

Data Index: 1119502 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4535. Min Act: -0.0001

Data Index: 1232858 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.3253. Min Act: -0.0000

Data Index: 1337229 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.5434. Min Act: -0.0001

Data Index: 1066842 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.6367. Min Act: -0.0000

Data Index: 1175841 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4554. Min Act: -0.0001

Data Index: 765153 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.3941. Min Act: -0.0000

Data Index: 706987 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4721. Min Act: -0.0001

Data Index: 645122 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.5387. Min Act: -0.0000

Data Index: 180042 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1031. Min Act: -0.0000

Data Index: 969541 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.2158. Min Act: -0.0001

Data Index: 1030946 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1787. Min Act: -0.0001

Data Index: 146981 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1830. Min Act: -0.0001

Data Index: 222731 (C4 (Web Text))

Max Activating Token Index: 435