Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 97 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.1972. Min Act: -0.1700

Data Index: 490526 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1194023 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.1657. Min Act: -0.1700

Data Index: 328561 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.1342. Min Act: -0.1700

Data Index: 1009014 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.1027. Min Act: -0.1700

Data Index: 956745 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0869. Min Act: -0.1700

Data Index: 241566 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0711. Min Act: -0.1700

Data Index: 1040021 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0711. Min Act: -0.1700

Data Index: 1310481 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0554. Min Act: -0.1700

Data Index: 785126 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0554. Min Act: -0.1700

Data Index: 57658 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0711. Min Act: -0.1700

Data Index: 914627 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0869. Min Act: -0.1700

Data Index: 1587968 (Python Code)

Max Activating Token Index: 626

Text #12

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0396. Min Act: -0.1700

Data Index: 482607 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0711. Min Act: -0.1700

Data Index: 150626 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0396. Min Act: -0.1700

Data Index: 1166593 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0554. Min Act: -0.1700

Data Index: 986840 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0238. Min Act: -0.1700

Data Index: 54288 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0396. Min Act: -0.1700

Data Index: 693093 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0238. Min Act: -0.1700

Data Index: 214244 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 3.1972. Min Range: -3.1972

Max Act: 3.0396. Min Act: -0.1700

Data Index: 300249 (C4 (Web Text))

Max Activating Token Index: 49