Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 311 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5956. Min Act: -0.1700

Data Index: 1443476 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1376722 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5330. Min Act: -0.1700

Data Index: 1639692 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1406442 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5173. Min Act: -0.1700

Data Index: 1311610 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5173. Min Act: -0.1699

Data Index: 1588084 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5643. Min Act: -0.1700

Data Index: 938770 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4860. Min Act: -0.1700

Data Index: 1608597 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1618223 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4860. Min Act: -0.1700

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4703. Min Act: -0.1700

Data Index: 1548936 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4390. Min Act: -0.1700

Data Index: 1623169 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.5016. Min Act: -0.1700

Data Index: 1541526 (Python Code)

Max Activating Token Index: 562

Text #13

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4703. Min Act: -0.1700

Data Index: 1539740 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4703. Min Act: -0.1700

Data Index: 1363133 (Python Code)

Max Activating Token Index: 684

Text #15

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1589221 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4703. Min Act: -0.1700

Data Index: 1555782 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1414753 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4390. Min Act: -0.1700

Data Index: 1501240 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 3.5956. Min Range: -3.5956

Max Act: 3.4390. Min Act: -0.1700

Data Index: 198187 (C4 (Web Text))

Max Activating Token Index: 840