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

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

Neuron 86 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.9955. Min Act: -0.1700

Data Index: 746734 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.9799. Min Act: -0.1700

Data Index: 1275922 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1467875 (Python Code)

Max Activating Token Index: 392

Text #3

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8861. Min Act: -0.1700

Data Index: 1466145 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8861. Min Act: -0.1700

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8548. Min Act: -0.1700

Data Index: 1517199 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1368564 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8548. Min Act: -0.1700

Data Index: 1528051 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8548. Min Act: -0.1700

Data Index: 1595220 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1418037 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1645791 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.7766. Min Act: -0.1700

Data Index: 408267 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1377095 (Python Code)

Max Activating Token Index: 778

Text #13

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.7766. Min Act: -0.1700

Data Index: 1631033 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8079. Min Act: -0.1699

Data Index: 1479005 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8079. Min Act: -0.1700

Data Index: 1402986 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.8079. Min Act: -0.1700

Data Index: 764660 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1523368 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.7297. Min Act: -0.1700

Data Index: 1548836 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.7140. Min Act: -0.1700

Data Index: 1426038 (Python Code)

Max Activating Token Index: 420