Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1890 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.8450. Min Act: -0.1700

Data Index: 1405401 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.7064. Min Act: -0.1700

Data Index: 1408744 (Python Code)

Max Activating Token Index: 239

Text #2

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.6137. Min Act: -0.1700

Data Index: 1471809 (Python Code)

Max Activating Token Index: 8

Text #3

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.5636. Min Act: -0.1700

Data Index: 1601317 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.5767. Min Act: -0.1700

Data Index: 636156 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.5243. Min Act: -0.1700

Data Index: 1008287 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.5299. Min Act: -0.1700

Data Index: 1593352 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.5265. Min Act: -0.1700

Data Index: 1435047 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.5258. Min Act: -0.1700

Data Index: 1508101 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.4789. Min Act: -0.1700

Data Index: 1370526 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.4281. Min Act: -0.1700

Data Index: 1532514 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.4130. Min Act: -0.1700

Data Index: 995190 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.4158. Min Act: -0.1700

Data Index: 1043853 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.4094. Min Act: -0.1700

Data Index: 1496124 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1152334 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.4019. Min Act: -0.1700

Data Index: 1464048 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.3886. Min Act: -0.1700

Data Index: 1567614 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.3957. Min Act: -0.1700

Data Index: 230554 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.3863. Min Act: -0.1700

Data Index: 358343 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 3.8450. Min Range: -3.8450

Max Act: 3.3992. Min Act: -0.1700

Data Index: 1393840 (Python Code)

Max Activating Token Index: 918