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

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

Neuron 952 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1384743 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1611564 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1615411 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4924. Min Act: -0.0001

Data Index: 1542567 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4718. Min Act: -0.0001

Data Index: 1617361 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4857. Min Act: -0.0001

Data Index: 1595800 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1497527 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4680. Min Act: -0.0001

Data Index: 1432043 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4370. Min Act: -0.0001

Data Index: 1385105 (Python Code)

Max Activating Token Index: 888

Text #9

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1392139 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1479064 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1501272 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1639038 (Python Code)

Max Activating Token Index: 549

Text #13

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1499729 (Python Code)

Max Activating Token Index: 315

Text #14

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4443. Min Act: -0.0001

Data Index: 1581323 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1143119 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1573809 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3871. Min Act: -0.0001

Data Index: 1466945 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1536197 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4351. Min Act: -0.0001

Data Index: 1373141 (Python Code)

Max Activating Token Index: 24