Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3405. Min Act: -0.0001

Data Index: 970513 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2755. Min Act: -0.0001

Data Index: 207662 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2934. Min Act: -0.0001

Data Index: 776012 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3115. Min Act: -0.0000

Data Index: 262422 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2563. Min Act: -0.0001

Data Index: 983483 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2620. Min Act: -0.0001

Data Index: 575977 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1006570 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2915. Min Act: -0.0001

Data Index: 603462 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2274. Min Act: -0.0001

Data Index: 807307 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2660. Min Act: -0.0001

Data Index: 33666 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2919. Min Act: -0.0001

Data Index: 789596 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2062. Min Act: -0.0001

Data Index: 206838 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2234. Min Act: -0.0001

Data Index: 476088 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1297751 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1197650 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2363. Min Act: -0.0001

Data Index: 915274 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1349521 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2418. Min Act: -0.0001

Data Index: 340416 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2201. Min Act: -0.0001

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2655. Min Act: -0.0001

Data Index: 533810 (C4 (Web Text))

Max Activating Token Index: 58