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

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

Neuron 1797 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: 4.6141. Min Range: -4.6141

Max Act: 4.6141. Min Act: -0.1700

Data Index: 1459573 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.5947. Min Act: -0.1700

Data Index: 1508111 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.5287. Min Act: -0.1700

Data Index: 1375978 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.5474. Min Act: -0.1700

Data Index: 1416259 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.4126. Min Act: -0.1700

Data Index: 1368931 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.4460. Min Act: -0.1700

Data Index: 1363172 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3962. Min Act: -0.1700

Data Index: 1425244 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3508. Min Act: -0.1700

Data Index: 1575308 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3248. Min Act: -0.1700

Data Index: 1501366 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3227. Min Act: -0.1700

Data Index: 1435063 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3655. Min Act: -0.1700

Data Index: 1430294 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3266. Min Act: -0.1700

Data Index: 1525212 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3187. Min Act: -0.1700

Data Index: 1523262 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.3002. Min Act: -0.1700

Data Index: 1516414 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.2733. Min Act: -0.1700

Data Index: 1502578 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.2802. Min Act: -0.1700

Data Index: 1473318 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.2774. Min Act: -0.1700

Data Index: 1415565 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.2732. Min Act: -0.1700

Data Index: 1363516 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.2192. Min Act: -0.1700

Data Index: 1362130 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 4.6141. Min Range: -4.6141

Max Act: 4.2810. Min Act: -0.1700

Data Index: 1366094 (Python Code)

Max Activating Token Index: 13