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

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

Neuron 1425 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: 3.5787. Min Range: -3.5787

Max Act: 3.5787. Min Act: -0.1700

Data Index: 1485449 (Python Code)

Max Activating Token Index: 326

Text #1

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5787. Min Act: -0.1700

Data Index: 1634461 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1575408 (Python Code)

Max Activating Token Index: 175

Text #3

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1415127 (Python Code)

Max Activating Token Index: 316

Text #4

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1575239 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1435627 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5161. Min Act: -0.1700

Data Index: 141781 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1591294 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5474. Min Act: -0.1699

Data Index: 1622527 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4534. Min Act: -0.1700

Data Index: 1000059 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1653852 (Python Code)

Max Activating Token Index: 571

Text #11

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1574717 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5161. Min Act: -0.1699

Data Index: 1633620 (Python Code)

Max Activating Token Index: 493

Text #13

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1563120 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4848. Min Act: -0.1700

Data Index: 286724 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4534. Min Act: -0.1700

Data Index: 1620335 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4221. Min Act: -0.1700

Data Index: 41524 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4534. Min Act: -0.1700

Data Index: 859243 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4534. Min Act: -0.1700

Data Index: 93095 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.5787. Min Range: -3.5787

Max Act: 3.4534. Min Act: -0.1700

Data Index: 744078 (C4 (Web Text))

Max Activating Token Index: 870