Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1152 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.8636. Min Act: -0.1700

Data Index: 1155180 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.5819. Min Act: -0.1700

Data Index: 1229429 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.5663. Min Act: -0.1700

Data Index: 34401 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.5349. Min Act: -0.1700

Data Index: 256044 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.5349. Min Act: -0.1700

Data Index: 849537 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.5506. Min Act: -0.1700

Data Index: 933859 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.5036. Min Act: -0.1700

Data Index: 382319 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4409. Min Act: -0.1700

Data Index: 387567 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4252. Min Act: -0.1700

Data Index: 1197809 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4566. Min Act: -0.1700

Data Index: 787020 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1162584 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4409. Min Act: -0.1700

Data Index: 670899 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4252. Min Act: -0.1700

Data Index: 448590 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4252. Min Act: -0.1700

Data Index: 1291151 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4409. Min Act: -0.1700

Data Index: 635982 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.4095. Min Act: -0.1700

Data Index: 460999 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1267990 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.3939. Min Act: -0.1700

Data Index: 489686 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.3625. Min Act: -0.1700

Data Index: 964618 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 3.8636. Min Range: -3.8636

Max Act: 3.3939. Min Act: -0.1700

Data Index: 1010997 (C4 (Web Text))

Max Activating Token Index: 336