Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 657 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.5056. Min Act: -0.1700

Data Index: 1528947 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.5056. Min Act: -0.1700

Data Index: 1507391 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4429. Min Act: -0.1700

Data Index: 1373814 (Python Code)

Max Activating Token Index: 496

Text #3

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4742. Min Act: -0.1700

Data Index: 1650140 (Python Code)

Max Activating Token Index: 273

Text #4

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4585. Min Act: -0.1700

Data Index: 1366561 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4585. Min Act: -0.1700

Data Index: 1013697 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4272. Min Act: -0.1700

Data Index: 1472384 (Python Code)

Max Activating Token Index: 879

Text #7

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3958. Min Act: -0.1700

Data Index: 1621089 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4115. Min Act: -0.1700

Data Index: 1626320 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3645. Min Act: -0.1700

Data Index: 1581132 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1643068 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4115. Min Act: -0.1700

Data Index: 1545341 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4272. Min Act: -0.1700

Data Index: 1455577 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.4115. Min Act: -0.1700

Data Index: 1551754 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1407953 (Python Code)

Max Activating Token Index: 464

Text #15

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3958. Min Act: -0.1700

Data Index: 1654218 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3958. Min Act: -0.1700

Data Index: 1549422 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3801. Min Act: -0.1700

Data Index: 1593387 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3958. Min Act: -0.1700

Data Index: 1600126 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 3.5056. Min Range: -3.5056

Max Act: 3.3174. Min Act: -0.1700

Data Index: 1433071 (Python Code)

Max Activating Token Index: 630