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

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

Neuron 1428 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0395. Min Range: -5.0395

Max Act: 5.0160. Min Act: -0.1700

Data Index: 125687 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 5.0395. Min Range: -5.0395

Max Act: 5.0395. Min Act: -0.1700

Data Index: 861495 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.8598. Min Act: -0.1700

Data Index: 981665 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.8676. Min Act: -0.1700

Data Index: 567586 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.8676. Min Act: -0.1700

Data Index: 1034523 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.8598. Min Act: -0.1700

Data Index: 490472 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.7738. Min Act: -0.1700

Data Index: 242238 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.7738. Min Act: -0.1700

Data Index: 1089729 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.8207. Min Act: -0.1700

Data Index: 1331098 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.7504. Min Act: -0.1700

Data Index: 15475 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.6801. Min Act: -0.1700

Data Index: 108330 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.7270. Min Act: -0.1700

Data Index: 12807 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.6332. Min Act: -0.1700

Data Index: 1092598 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.6567. Min Act: -0.1700

Data Index: 1320287 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.6332. Min Act: -0.1700

Data Index: 1074269 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.6176. Min Act: -0.1699

Data Index: 1179610 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.6098. Min Act: -0.1700

Data Index: 957432 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.5863. Min Act: -0.1700

Data Index: 539381 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.5707. Min Act: -0.1700

Data Index: 912423 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 5.0395. Min Range: -5.0395

Max Act: 4.5395. Min Act: -0.1700

Data Index: 493647 (C4 (Web Text))

Max Activating Token Index: 224