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

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

Neuron 1032 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: 3.3263. Min Range: -3.3263

Max Act: 3.3106. Min Act: -0.1700

Data Index: 779689 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.3263. Min Act: -0.1700

Data Index: 1199106 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2948. Min Act: -0.1700

Data Index: 300338 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.3106. Min Act: -0.1700

Data Index: 320659 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2948. Min Act: -0.1700

Data Index: 51110 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.3106. Min Act: -0.1700

Data Index: 1313731 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2634. Min Act: -0.1700

Data Index: 713458 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2948. Min Act: -0.1700

Data Index: 207855 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2791. Min Act: -0.1700

Data Index: 1001168 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2791. Min Act: -0.1700

Data Index: 356585 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2634. Min Act: -0.1700

Data Index: 404350 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2791. Min Act: -0.1700

Data Index: 209299 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2634. Min Act: -0.1700

Data Index: 1149200 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2477. Min Act: -0.1700

Data Index: 927464 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2477. Min Act: -0.1700

Data Index: 577284 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2320. Min Act: -0.1700

Data Index: 562998 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2634. Min Act: -0.1700

Data Index: 36027 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2477. Min Act: -0.1700

Data Index: 476743 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2477. Min Act: -0.1700

Data Index: 864125 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2634. Min Act: -0.1700

Data Index: 75347 (C4 (Web Text))

Max Activating Token Index: 562