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

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

Neuron 176 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.9715. Min Act: -0.1700

Data Index: 654540 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 5.0340. Min Range: -5.0340

Max Act: 5.0340. Min Act: -0.1700

Data Index: 459294 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.9090. Min Act: -0.1700

Data Index: 350284 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.8153. Min Act: -0.1700

Data Index: 1321191 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.8153. Min Act: -0.1700

Data Index: 532410 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.7528. Min Act: -0.1700

Data Index: 299586 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.7215. Min Act: -0.1700

Data Index: 374818 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.7215. Min Act: -0.1700

Data Index: 10560 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.7528. Min Act: -0.1700

Data Index: 444385 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6903. Min Act: -0.1700

Data Index: 962800 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.7215. Min Act: -0.1700

Data Index: 217535 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6903. Min Act: -0.1700

Data Index: 775977 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6277. Min Act: -0.1700

Data Index: 16145 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6590. Min Act: -0.1700

Data Index: 683281 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6903. Min Act: -0.1700

Data Index: 365927 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6590. Min Act: -0.1700

Data Index: 622085 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6903. Min Act: -0.1700

Data Index: 915486 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6277. Min Act: -0.1700

Data Index: 355438 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.5965. Min Act: -0.1700

Data Index: 400491 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 5.0340. Min Range: -5.0340

Max Act: 4.6277. Min Act: -0.1700

Data Index: 841107 (C4 (Web Text))

Max Activating Token Index: 69