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

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

Neuron 940 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.2263. Min Act: -0.1700

Data Index: 434175 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.2263. Min Act: -0.1700

Data Index: 783152 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1948. Min Act: -0.1700

Data Index: 523430 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1327140 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1948. Min Act: -0.1700

Data Index: 8305 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1948. Min Act: -0.1700

Data Index: 527519 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1328737 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1633. Min Act: -0.1700

Data Index: 637962 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1633. Min Act: -0.1700

Data Index: 463055 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1476. Min Act: -0.1700

Data Index: 974150 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1633. Min Act: -0.1700

Data Index: 175576 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1161. Min Act: -0.1700

Data Index: 1230368 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1318. Min Act: -0.1700

Data Index: 411756 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1318. Min Act: -0.1700

Data Index: 967263 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1318. Min Act: -0.1700

Data Index: 921332 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1161. Min Act: -0.1700

Data Index: 295959 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1318. Min Act: -0.1700

Data Index: 992607 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1003. Min Act: -0.1700

Data Index: 726491 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.0845. Min Act: -0.1700

Data Index: 1005291 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 3.2263. Min Range: -3.2263

Max Act: 3.1161. Min Act: -0.1700

Data Index: 471776 (C4 (Web Text))

Max Activating Token Index: 4