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

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

Neuron 2078 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: 3.1530. Min Range: -3.1530

Max Act: 3.1530. Min Act: -0.0001

Data Index: 980391 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.9115. Min Act: -0.0001

Data Index: 1329506 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.8825. Min Act: -0.0001

Data Index: 273198 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.8322. Min Act: -0.0001

Data Index: 1030323 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.8448. Min Act: -0.0001

Data Index: 597557 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.9574. Min Act: -0.0001

Data Index: 752691 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.7352. Min Act: -0.0001

Data Index: 1000638 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5863. Min Act: -0.0001

Data Index: 667988 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.6902. Min Act: -0.0001

Data Index: 1071208 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5798. Min Act: -0.0001

Data Index: 1058069 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.7986. Min Act: -0.0001

Data Index: 289936 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.6359. Min Act: -0.0001

Data Index: 739394 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.6003. Min Act: -0.0001

Data Index: 926384 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5820. Min Act: -0.0001

Data Index: 226403 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5870. Min Act: -0.0001

Data Index: 633394 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5647. Min Act: -0.0001

Data Index: 830356 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5630. Min Act: -0.0001

Data Index: 244961 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.3839. Min Act: -0.0001

Data Index: 1026230 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.5485. Min Act: -0.0001

Data Index: 83985 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.1530. Min Range: -3.1530

Max Act: 2.6602. Min Act: -0.0001

Data Index: 1379207 (Python Code)

Max Activating Token Index: 2