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

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

Neuron 201 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.5745. Min Act: -0.1700

Data Index: 1511114 (Python Code)

Max Activating Token Index: 862

Text #1

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.5432. Min Act: -0.1700

Data Index: 1395562 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.4807. Min Act: -0.1700

Data Index: 1544457 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.4495. Min Act: -0.1700

Data Index: 1414968 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.5120. Min Act: -0.1700

Data Index: 1451394 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.4182. Min Act: -0.1700

Data Index: 1637907 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.3245. Min Act: -0.1700

Data Index: 1475060 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.3557. Min Act: -0.1700

Data Index: 1420263 (Python Code)

Max Activating Token Index: 541

Text #8

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.3245. Min Act: -0.1700

Data Index: 1360998 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.2620. Min Act: -0.1700

Data Index: 1533025 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.2307. Min Act: -0.1700

Data Index: 1597577 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.2620. Min Act: -0.1700

Data Index: 1445169 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.2620. Min Act: -0.1700

Data Index: 1387218 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.2307. Min Act: -0.1700

Data Index: 1432292 (Python Code)

Max Activating Token Index: 315

Text #14

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.2307. Min Act: -0.1700

Data Index: 1540757 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.1995. Min Act: -0.1700

Data Index: 1575257 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.1370. Min Act: -0.1700

Data Index: 1482945 (Python Code)

Max Activating Token Index: 405

Text #17

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.1370. Min Act: -0.1700

Data Index: 1410896 (Python Code)

Max Activating Token Index: 488

Text #18

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.1682. Min Act: -0.1700

Data Index: 1513448 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 5.5745. Min Range: -5.5745

Max Act: 5.1682. Min Act: -0.1700

Data Index: 1477120 (Python Code)

Max Activating Token Index: 246