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

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

Neuron 4115 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1393554 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1642691 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1594795 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1433041 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1388464 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1487737 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1393477 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1453226 (Python Code)

Max Activating Token Index: 315

Text #8

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1613009 (Python Code)

Max Activating Token Index: 477

Text #9

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1477563 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1496886 (Python Code)

Max Activating Token Index: 567

Text #11

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1637463 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1503807 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1565112 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1554615 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1455628 (Python Code)

Max Activating Token Index: 1002

Text #16

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1486103 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1537680 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1479461 (Python Code)

Max Activating Token Index: 776

Text #19

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1646267 (Python Code)

Max Activating Token Index: 286