Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1588 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0047. Min Range: -4.0047

Max Act: 4.0047. Min Act: -0.1700

Data Index: 1479593 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.8123. Min Act: -0.1700

Data Index: 1379177 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.8269. Min Act: -0.1700

Data Index: 1564422 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.8189. Min Act: -0.1700

Data Index: 1511534 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.8114. Min Act: -0.1700

Data Index: 1655735 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.7175. Min Act: -0.1700

Data Index: 1611998 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.6360. Min Act: -0.1700

Data Index: 1600850 (Python Code)

Max Activating Token Index: 745

Text #7

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.6154. Min Act: -0.1700

Data Index: 1547137 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.6231. Min Act: -0.1700

Data Index: 1522741 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1476615 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5999. Min Act: -0.1700

Data Index: 1531130 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5925. Min Act: -0.1700

Data Index: 1577299 (Python Code)

Max Activating Token Index: 987

Text #12

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1533330 (Python Code)

Max Activating Token Index: 751

Text #13

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.6033. Min Act: -0.1700

Data Index: 1513648 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1588635 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5823. Min Act: -0.1700

Data Index: 1398126 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5802. Min Act: -0.1700

Data Index: 1399095 (Python Code)

Max Activating Token Index: 703

Text #17

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5804. Min Act: -0.1700

Data Index: 1412006 (Python Code)

Max Activating Token Index: 659

Text #18

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5760. Min Act: -0.1700

Data Index: 1654713 (Python Code)

Max Activating Token Index: 506

Text #19

Max Range: 4.0047. Min Range: -4.0047

Max Act: 3.5801. Min Act: -0.1700

Data Index: 1439500 (Python Code)

Max Activating Token Index: 12