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

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

Neuron 421 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: 3.1942. Min Range: -3.1942

Max Act: 3.1942. Min Act: -0.1700

Data Index: 879690 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1628. Min Act: -0.1700

Data Index: 431966 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1658. Min Act: -0.1700

Data Index: 548282 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0680. Min Act: -0.1700

Data Index: 125444 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0392. Min Act: -0.1700

Data Index: 1312669 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0293. Min Act: -0.1700

Data Index: 1336358 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0013. Min Act: -0.1700

Data Index: 603878 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9959. Min Act: -0.1700

Data Index: 1353969 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9542. Min Act: -0.1691

Data Index: 1550834 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9447. Min Act: -0.1699

Data Index: 1024102 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9062. Min Act: -0.1700

Data Index: 404641 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8914. Min Act: -0.1700

Data Index: 613537 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.9056. Min Act: -0.1700

Data Index: 463624 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8702. Min Act: -0.1700

Data Index: 561060 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8698. Min Act: -0.1699

Data Index: 763130 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8532. Min Act: -0.1700

Data Index: 303389 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8603. Min Act: -0.1700

Data Index: 732124 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8462. Min Act: -0.1700

Data Index: 1626483 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8547. Min Act: -0.1698

Data Index: 1615308 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 3.1942. Min Range: -3.1942

Max Act: 2.8219. Min Act: -0.1700

Data Index: 1564360 (Python Code)

Max Activating Token Index: 893