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

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

Neuron 1846 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: 3.4373. Min Range: -3.4373

Max Act: 3.4373. Min Act: -0.1700

Data Index: 577210 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.4216. Min Act: -0.1700

Data Index: 907321 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.4059. Min Act: -0.1700

Data Index: 356839 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3902. Min Act: -0.1700

Data Index: 1098922 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3589. Min Act: -0.1700

Data Index: 1240842 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3589. Min Act: -0.1700

Data Index: 458792 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3118. Min Act: -0.1700

Data Index: 1486686 (Python Code)

Max Activating Token Index: 65

Text #7

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3275. Min Act: -0.1700

Data Index: 186612 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3118. Min Act: -0.1700

Data Index: 486579 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3118. Min Act: -0.1700

Data Index: 178737 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3118. Min Act: -0.1700

Data Index: 730550 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3118. Min Act: -0.1700

Data Index: 1207788 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2961. Min Act: -0.1700

Data Index: 1178577 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2961. Min Act: -0.1700

Data Index: 917096 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2961. Min Act: -0.1700

Data Index: 273429 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2804. Min Act: -0.1700

Data Index: 767956 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2961. Min Act: -0.1700

Data Index: 130603 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2961. Min Act: -0.1700

Data Index: 165343 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.3118. Min Act: -0.1700

Data Index: 1067325 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.4373. Min Range: -3.4373

Max Act: 3.2646. Min Act: -0.1700

Data Index: 963603 (C4 (Web Text))

Max Activating Token Index: 598