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

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

Neuron 1026 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: 3.2657. Min Range: -3.2657

Max Act: 3.2657. Min Act: -0.1700

Data Index: 268224 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2500. Min Act: -0.1700

Data Index: 13540 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2342. Min Act: -0.1700

Data Index: 260166 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2185. Min Act: -0.1700

Data Index: 1302221 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2028. Min Act: -0.1700

Data Index: 166774 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2028. Min Act: -0.1700

Data Index: 700837 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.2028. Min Act: -0.1700

Data Index: 978404 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1713. Min Act: -0.1700

Data Index: 112941 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1556. Min Act: -0.1700

Data Index: 1302019 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1556. Min Act: -0.1700

Data Index: 418907 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1398. Min Act: -0.1700

Data Index: 653737 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1241. Min Act: -0.1700

Data Index: 564377 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1241. Min Act: -0.1700

Data Index: 589678 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0925. Min Act: -0.1700

Data Index: 1231849 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1083. Min Act: -0.1700

Data Index: 456679 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0768. Min Act: -0.1700

Data Index: 698158 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1083. Min Act: -0.1700

Data Index: 760706 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.0925. Min Act: -0.1700

Data Index: 752212 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1083. Min Act: -0.1700

Data Index: 387218 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 3.2657. Min Range: -3.2657

Max Act: 3.1083. Min Act: -0.1700

Data Index: 11696 (C4 (Web Text))

Max Activating Token Index: 925