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

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

Neuron 1116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.4460. Min Act: -0.1700

Data Index: 802486 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.4930. Min Act: -0.1700

Data Index: 706152 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3990. Min Act: -0.1700

Data Index: 662272 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.4617. Min Act: -0.1700

Data Index: 1094757 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.4147. Min Act: -0.1700

Data Index: 280787 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.4303. Min Act: -0.1700

Data Index: 393797 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.4303. Min Act: -0.1700

Data Index: 637650 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3519. Min Act: -0.1700

Data Index: 806717 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3990. Min Act: -0.1700

Data Index: 192979 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3990. Min Act: -0.1700

Data Index: 1115195 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3676. Min Act: -0.1700

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3676. Min Act: -0.1700

Data Index: 1116046 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3048. Min Act: -0.1700

Data Index: 242125 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3519. Min Act: -0.1700

Data Index: 1167169 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3205. Min Act: -0.1700

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3362. Min Act: -0.1700

Data Index: 495478 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3048. Min Act: -0.1700

Data Index: 331523 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3048. Min Act: -0.1700

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3048. Min Act: -0.1700

Data Index: 553234 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 3.4930. Min Range: -3.4930

Max Act: 3.3205. Min Act: -0.1700

Data Index: 955871 (C4 (Web Text))

Max Activating Token Index: 916