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

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

Neuron 252 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: 5.3163. Min Range: -5.3163

Max Act: 5.2850. Min Act: -0.1700

Data Index: 906715 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.3163. Min Act: -0.1700

Data Index: 527448 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.3163. Min Act: -0.1700

Data Index: 574021 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.3163. Min Act: -0.1700

Data Index: 1184024 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2850. Min Act: -0.1700

Data Index: 487867 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.3163. Min Act: -0.1698

Data Index: 192148 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2850. Min Act: -0.1699

Data Index: 441027 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2850. Min Act: -0.1700

Data Index: 598440 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2850. Min Act: -0.1700

Data Index: 578148 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2538. Min Act: -0.1700

Data Index: 1125561 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2538. Min Act: -0.1700

Data Index: 898851 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2225. Min Act: -0.1699

Data Index: 513586 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2538. Min Act: -0.1700

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2538. Min Act: -0.1700

Data Index: 653020 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2538. Min Act: -0.1698

Data Index: 241858 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2538. Min Act: -0.1700

Data Index: 289050 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2225. Min Act: -0.1700

Data Index: 1110442 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2225. Min Act: -0.1696

Data Index: 1025377 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.1913. Min Act: -0.1700

Data Index: 290420 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 5.3163. Min Range: -5.3163

Max Act: 5.2225. Min Act: -0.1700

Data Index: 635971 (C4 (Web Text))

Max Activating Token Index: 478