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

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

Neuron 965 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: 4.1157. Min Range: -4.1157

Max Act: 4.1157. Min Act: -0.1700

Data Index: 1629651 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 4.1157. Min Range: -4.1157

Max Act: 4.0137. Min Act: -0.1700

Data Index: 1384394 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.9857. Min Act: -0.1700

Data Index: 753052 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.9809. Min Act: -0.1699

Data Index: 1442282 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.9654. Min Act: -0.1700

Data Index: 923767 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.9157. Min Act: -0.1700

Data Index: 396744 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8941. Min Act: -0.1700

Data Index: 1402288 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8623. Min Act: -0.1700

Data Index: 1601904 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8760. Min Act: -0.1700

Data Index: 1651789 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8629. Min Act: -0.1700

Data Index: 1376002 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8822. Min Act: -0.1700

Data Index: 1440850 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8658. Min Act: -0.1700

Data Index: 1607431 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8640. Min Act: -0.1700

Data Index: 1370264 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8563. Min Act: -0.1700

Data Index: 1202360 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8566. Min Act: -0.1700

Data Index: 1247806 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8422. Min Act: -0.1700

Data Index: 587344 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8449. Min Act: -0.1700

Data Index: 1439028 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8349. Min Act: -0.1700

Data Index: 12385 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8354. Min Act: -0.1700

Data Index: 1251435 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 4.1157. Min Range: -4.1157

Max Act: 3.8206. Min Act: -0.1700

Data Index: 1318066 (C4 (Web Text))

Max Activating Token Index: 143