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

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

Neuron 869 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: 3.4095. Min Range: -3.4095

Max Act: 3.3781. Min Act: -0.1700

Data Index: 1174632 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.4095. Min Act: -0.1700

Data Index: 720870 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3938. Min Act: -0.1700

Data Index: 834195 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3938. Min Act: -0.1700

Data Index: 1214698 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3310. Min Act: -0.1700

Data Index: 403016 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3467. Min Act: -0.1700

Data Index: 950957 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3467. Min Act: -0.1700

Data Index: 1214226 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3467. Min Act: -0.1700

Data Index: 124336 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3467. Min Act: -0.1700

Data Index: 115545 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2996. Min Act: -0.1700

Data Index: 851188 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2839. Min Act: -0.1700

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2996. Min Act: -0.1700

Data Index: 683400 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2525. Min Act: -0.1700

Data Index: 791305 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2682. Min Act: -0.1700

Data Index: 89070 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2996. Min Act: -0.1700

Data Index: 1165002 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2525. Min Act: -0.1700

Data Index: 1220106 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2682. Min Act: -0.1700

Data Index: 409794 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2682. Min Act: -0.1700

Data Index: 666791 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2525. Min Act: -0.1700

Data Index: 728555 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2368. Min Act: -0.1700

Data Index: 1082278 (C4 (Web Text))

Max Activating Token Index: 210