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

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

Neuron 377 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: 2.0413. Min Range: -2.0413

Max Act: 2.0413. Min Act: -0.0000

Data Index: 958617 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.8973. Min Act: -0.0000

Data Index: 836325 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.8588. Min Act: -0.0000

Data Index: 1193319 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.9593. Min Act: -0.0000

Data Index: 1357188 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.8146. Min Act: -0.0000

Data Index: 422705 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.6486. Min Act: -0.0000

Data Index: 829684 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.7963. Min Act: -0.0000

Data Index: 235485 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.5991. Min Act: -0.0000

Data Index: 565238 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.5940. Min Act: -0.0000

Data Index: 280323 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1052560 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4954. Min Act: -0.0000

Data Index: 593286 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.5735. Min Act: -0.0000

Data Index: 853514 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4405. Min Act: -0.0000

Data Index: 655213 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.5195. Min Act: -0.0000

Data Index: 380140 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4070. Min Act: -0.0000

Data Index: 590863 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4370. Min Act: -0.0000

Data Index: 209367 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4923. Min Act: -0.0000

Data Index: 486949 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.5756. Min Act: -0.0000

Data Index: 119439 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4387. Min Act: -0.0000

Data Index: 781955 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.0413. Min Range: -2.0413

Max Act: 1.4409. Min Act: -0.0000

Data Index: 187497 (C4 (Web Text))

Max Activating Token Index: 11