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

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

Neuron 1952 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: 5.5913. Min Range: -5.5913

Max Act: 5.5913. Min Act: -0.1700

Data Index: 862599 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.4663. Min Act: -0.1700

Data Index: 1055875 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.4350. Min Act: -0.1700

Data Index: 226548 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.4038. Min Act: -0.1700

Data Index: 1090418 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.4038. Min Act: -0.1700

Data Index: 293515 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.4038. Min Act: -0.1700

Data Index: 255733 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3413. Min Act: -0.1700

Data Index: 206793 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3725. Min Act: -0.1700

Data Index: 461270 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3413. Min Act: -0.1700

Data Index: 702056 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2788. Min Act: -0.1700

Data Index: 308419 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3100. Min Act: -0.1700

Data Index: 26082 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3413. Min Act: -0.1700

Data Index: 502471 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3100. Min Act: -0.1700

Data Index: 421862 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.3100. Min Act: -0.1700

Data Index: 434558 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2475. Min Act: -0.1700

Data Index: 188691 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2163. Min Act: -0.1700

Data Index: 490281 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2475. Min Act: -0.1700

Data Index: 931665 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2163. Min Act: -0.1700

Data Index: 970548 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2475. Min Act: -0.1700

Data Index: 1016738 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 5.5913. Min Range: -5.5913

Max Act: 5.2163. Min Act: -0.1700

Data Index: 711229 (C4 (Web Text))

Max Activating Token Index: 443