Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1588056 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1494354 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8991. Min Act: -0.1700

Data Index: 1567968 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8991. Min Act: -0.1700

Data Index: 1501251 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8835. Min Act: -0.1700

Data Index: 1475935 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8522. Min Act: -0.1700

Data Index: 1397212 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8366. Min Act: -0.1700

Data Index: 1432473 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8366. Min Act: -0.1700

Data Index: 1446647 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8366. Min Act: -0.1700

Data Index: 1630356 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8210. Min Act: -0.1700

Data Index: 1626593 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8522. Min Act: -0.1700

Data Index: 1485245 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1526525 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8366. Min Act: -0.1700

Data Index: 1462780 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7740. Min Act: -0.1700

Data Index: 1453578 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7584. Min Act: -0.1700

Data Index: 1514938 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7740. Min Act: -0.1700

Data Index: 1429495 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7427. Min Act: -0.1700

Data Index: 1485197 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7740. Min Act: -0.1700

Data Index: 1476878 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7584. Min Act: -0.1700

Data Index: 1595264 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.7584. Min Act: -0.1700

Data Index: 1428872 (Python Code)

Max Activating Token Index: 535