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

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

Neuron 4786 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.9347. Min Act: -0.0001

Data Index: 1510017 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.8974. Min Act: -0.0001

Data Index: 1646140 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.6283. Min Act: -0.0001

Data Index: 1651952 (Python Code)

Max Activating Token Index: 824

Text #3

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.5425. Min Act: -0.0001

Data Index: 1551864 (Python Code)

Max Activating Token Index: 316

Text #4

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.8711. Min Act: -0.0001

Data Index: 1554737 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.6922. Min Act: -0.0001

Data Index: 1558257 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.5402. Min Act: -0.0001

Data Index: 1640541 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.6581. Min Act: -0.0001

Data Index: 1414438 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.5982. Min Act: -0.0001

Data Index: 1582682 (Python Code)

Max Activating Token Index: 462

Text #9

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.5860. Min Act: -0.0001

Data Index: 1403899 (Python Code)

Max Activating Token Index: 598

Text #10

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.5677. Min Act: -0.0001

Data Index: 1525344 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7251. Min Act: -0.0001

Data Index: 1492778 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.3791. Min Act: -0.0001

Data Index: 1371168 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.6659. Min Act: -0.0001

Data Index: 1510242 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.4769. Min Act: -0.0001

Data Index: 1653871 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.4274. Min Act: -0.0001

Data Index: 1443550 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.4261. Min Act: -0.0001

Data Index: 1496461 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.5735. Min Act: -0.0001

Data Index: 1472697 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.4163. Min Act: -0.0001

Data Index: 1435069 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.3857. Min Act: -0.0001

Data Index: 1431546 (Python Code)

Max Activating Token Index: 241