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

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

Neuron 5353 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6900. Min Range: -5.6900

Max Act: 5.6900. Min Act: -0.0000

Data Index: 1336100 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 5.6900. Min Range: -5.6900

Max Act: 5.2921. Min Act: -0.0000

Data Index: 1315858 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 5.6900. Min Range: -5.6900

Max Act: 5.5090. Min Act: -0.0000

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 5.6900. Min Range: -5.6900

Max Act: 5.0920. Min Act: -0.0000

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 5.6900. Min Range: -5.6900

Max Act: 5.0655. Min Act: -0.0000

Data Index: 363063 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 5.6900. Min Range: -5.6900

Max Act: 5.0620. Min Act: -0.0000

Data Index: 1175114 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.9663. Min Act: -0.0000

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.9699. Min Act: -0.0000

Data Index: 457143 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.9158. Min Act: -0.0000

Data Index: 614378 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.5615. Min Act: -0.0000

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.8448. Min Act: -0.0000

Data Index: 252815 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.6462. Min Act: -0.0000

Data Index: 247957 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.6138. Min Act: -0.0000

Data Index: 267887 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.4389. Min Act: -0.0000

Data Index: 368286 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.8016. Min Act: -0.0000

Data Index: 773783 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.5887. Min Act: -0.0000

Data Index: 664698 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.5708. Min Act: -0.0000

Data Index: 88256 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.7381. Min Act: -0.0000

Data Index: 1082464 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.3103. Min Act: -0.0000

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 5.6900. Min Range: -5.6900

Max Act: 4.2573. Min Act: -0.0000

Data Index: 336257 (C4 (Web Text))

Max Activating Token Index: 641