Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.7348. Min Act: -0.0001

Data Index: 90628 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6460. Min Act: -0.0001

Data Index: 386908 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1117633 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5835. Min Act: -0.0001

Data Index: 1182480 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5991. Min Act: -0.0001

Data Index: 1153389 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6439. Min Act: -0.0001

Data Index: 1051792 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6336. Min Act: -0.0001

Data Index: 433058 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6091. Min Act: -0.0001

Data Index: 758443 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6205. Min Act: -0.0001

Data Index: 670005 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5986. Min Act: -0.0001

Data Index: 490107 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6069. Min Act: -0.0001

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6026. Min Act: -0.0001

Data Index: 648496 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5773. Min Act: -0.0001

Data Index: 967938 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6706. Min Act: -0.0001

Data Index: 447405 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4756. Min Act: -0.0001

Data Index: 111433 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.6275. Min Act: -0.0001

Data Index: 48505 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1269538 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1303887 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5252. Min Act: -0.0001

Data Index: 162723 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5434. Min Act: -0.0001

Data Index: 471081 (C4 (Web Text))

Max Activating Token Index: 463