Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 284 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.5011. Min Act: -0.0002

Data Index: 1522425 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.5209. Min Act: -0.0002

Data Index: 1435363 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4893. Min Act: -0.0002

Data Index: 1510257 (Python Code)

Max Activating Token Index: 368

Text #3

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4709. Min Act: -0.0002

Data Index: 1471582 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.5007. Min Act: -0.0002

Data Index: 1395710 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4463. Min Act: -0.0002

Data Index: 1551610 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1539102 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1379292 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4367. Min Act: -0.0002

Data Index: 1611664 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4440. Min Act: -0.0002

Data Index: 1641655 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4250. Min Act: -0.0002

Data Index: 1610538 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3700. Min Act: -0.0002

Data Index: 1622073 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.4029. Min Act: -0.0002

Data Index: 1656164 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3804. Min Act: -0.0002

Data Index: 1427498 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3991. Min Act: -0.0001

Data Index: 1598102 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3857. Min Act: -0.0003

Data Index: 1627688 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1494332 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3762. Min Act: -0.0002

Data Index: 599058 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3314. Min Act: -0.0002

Data Index: 1603946 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.5209. Min Range: -0.5209

Max Act: 0.3853. Min Act: -0.0002

Data Index: 1438254 (Python Code)

Max Activating Token Index: 435