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

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

Neuron 235 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.9020. Min Act: -0.1700

Data Index: 139352 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.8708. Min Act: -0.1700

Data Index: 1437462 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.8082. Min Act: -0.1700

Data Index: 630385 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.8708. Min Act: -0.1700

Data Index: 1197995 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.8082. Min Act: -0.1698

Data Index: 758611 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7769. Min Act: -0.1699

Data Index: 136741 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7769. Min Act: -0.1699

Data Index: 1588997 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7769. Min Act: -0.1700

Data Index: 47808 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7769. Min Act: -0.1700

Data Index: 809990 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1700

Data Index: 594312 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7769. Min Act: -0.1699

Data Index: 889590 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1700

Data Index: 328781 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1700

Data Index: 405325 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1699

Data Index: 1066345 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1700

Data Index: 1306543 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1699

Data Index: 499888 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7143. Min Act: -0.1700

Data Index: 302958 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1700

Data Index: 826618 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7456. Min Act: -0.1700

Data Index: 1025837 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 3.9020. Min Range: -3.9020

Max Act: 3.7143. Min Act: -0.1700

Data Index: 715325 (C4 (Web Text))

Max Activating Token Index: 523