Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1369 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1365928 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1059527 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3159. Min Act: -0.0001

Data Index: 201058 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3085. Min Act: 0.0001

Data Index: 1542603 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3148. Min Act: 0.0002

Data Index: 1496890 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3035. Min Act: 0.0002

Data Index: 1514932 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3086. Min Act: 0.0002

Data Index: 1648127 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2768. Min Act: 0.0002

Data Index: 1604338 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2834. Min Act: 0.0002

Data Index: 1594548 (Python Code)

Max Activating Token Index: 559

Text #9

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1643130 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2805. Min Act: 0.0002

Data Index: 1558926 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2872. Min Act: 0.0001

Data Index: 1521120 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1182036 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2710. Min Act: 0.0002

Data Index: 1441476 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1647446 (Python Code)

Max Activating Token Index: 740

Text #15

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2679. Min Act: 0.0002

Data Index: 1383474 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1602525 (Python Code)

Max Activating Token Index: 994

Text #17

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1428164 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1618392 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1475934 (Python Code)

Max Activating Token Index: 375