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

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

Neuron 517 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.4441. Min Act: -0.1700

Data Index: 932621 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.4441. Min Act: -0.1700

Data Index: 327902 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3814. Min Act: -0.1700

Data Index: 221109 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.4128. Min Act: -0.1700

Data Index: 278199 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.4441. Min Act: -0.1700

Data Index: 488753 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3500. Min Act: -0.1700

Data Index: 888199 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3814. Min Act: -0.1700

Data Index: 1199121 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3500. Min Act: -0.1700

Data Index: 698479 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1230315 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3186. Min Act: -0.1700

Data Index: 900458 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2872. Min Act: -0.1700

Data Index: 1254919 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3186. Min Act: -0.1700

Data Index: 1344560 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2872. Min Act: -0.1700

Data Index: 264169 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3186. Min Act: -0.1700

Data Index: 1356666 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2872. Min Act: -0.1700

Data Index: 1231660 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2872. Min Act: -0.1700

Data Index: 721807 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2872. Min Act: -0.1700

Data Index: 752680 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2872. Min Act: -0.1700

Data Index: 371451 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.2558. Min Act: -0.1700

Data Index: 769868 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 3.4441. Min Range: -3.4441

Max Act: 3.3186. Min Act: -0.1700

Data Index: 111792 (C4 (Web Text))

Max Activating Token Index: 471