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

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

Neuron 703 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: 3.2900. Min Range: -3.2900

Max Act: 3.2900. Min Act: -0.1700

Data Index: 753981 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.2706. Min Act: -0.1700

Data Index: 661055 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.2231. Min Act: -0.1700

Data Index: 248891 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1147704 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1815. Min Act: -0.1700

Data Index: 744513 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1255219 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1824. Min Act: -0.1700

Data Index: 1278114 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1713. Min Act: -0.1700

Data Index: 1021137 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1612. Min Act: -0.1700

Data Index: 269861 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1467. Min Act: -0.1700

Data Index: 1277691 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1486. Min Act: -0.1700

Data Index: 32775 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1447. Min Act: -0.1700

Data Index: 153923 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1579. Min Act: -0.1700

Data Index: 715581 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1013597 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1270. Min Act: -0.1700

Data Index: 737547 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1418. Min Act: -0.1700

Data Index: 578195 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1007. Min Act: -0.1699

Data Index: 429794 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.1014. Min Act: -0.1700

Data Index: 566735 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.0973. Min Act: -0.1700

Data Index: 113953 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 3.2900. Min Range: -3.2900

Max Act: 3.0952. Min Act: -0.1700

Data Index: 951577 (C4 (Web Text))

Max Activating Token Index: 179