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

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

Neuron 1259 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: 3.7523. Min Range: -3.7523

Max Act: 3.7523. Min Act: -0.1700

Data Index: 501281 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.7210. Min Act: -0.1700

Data Index: 435581 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6898. Min Act: -0.1700

Data Index: 1572242 (Python Code)

Max Activating Token Index: 182

Text #3

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6898. Min Act: -0.1700

Data Index: 1359910 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6898. Min Act: -0.1700

Data Index: 1286474 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6585. Min Act: -0.1700

Data Index: 1400824 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6271. Min Act: -0.1700

Data Index: 1601673 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6585. Min Act: -0.1700

Data Index: 1539409 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6898. Min Act: -0.1700

Data Index: 195772 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6271. Min Act: -0.1700

Data Index: 1631726 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5958. Min Act: -0.1700

Data Index: 1382813 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.6271. Min Act: -0.1700

Data Index: 1515799 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5958. Min Act: -0.1700

Data Index: 1571286 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5958. Min Act: -0.1700

Data Index: 1563447 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5958. Min Act: -0.1700

Data Index: 924721 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5332. Min Act: -0.1700

Data Index: 1424784 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5645. Min Act: -0.1700

Data Index: 1534667 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5958. Min Act: -0.1700

Data Index: 1448001 (Python Code)

Max Activating Token Index: 405

Text #18

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5645. Min Act: -0.1700

Data Index: 1585181 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 3.7523. Min Range: -3.7523

Max Act: 3.5332. Min Act: -0.1700

Data Index: 513565 (C4 (Web Text))

Max Activating Token Index: 328