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

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

Neuron 980 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1511064 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1446461 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1580450 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1466881 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1518312 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1457606 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1454893 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1393779 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1488685 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1440878 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1585205 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1574911 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1552512 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1397518 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1413634 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.0972. Min Act: -0.1700

Data Index: 1438389 (Python Code)

Max Activating Token Index: 184

Text #16

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.1129. Min Act: -0.1700

Data Index: 1434693 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1379407 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1566149 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.0972. Min Act: -0.1700

Data Index: 1368316 (Python Code)

Max Activating Token Index: 44