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

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

Neuron 1076 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.2999. Min Act: -0.1696

Data Index: 307805 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.3311. Min Act: -0.1700

Data Index: 248264 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1124183 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.2061. Min Act: -0.1700

Data Index: 630624 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1436. Min Act: -0.1700

Data Index: 1141344 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1749. Min Act: -0.1700

Data Index: 1115250 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.2061. Min Act: -0.1700

Data Index: 98306 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1749. Min Act: -0.1700

Data Index: 543243 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1436. Min Act: -0.1700

Data Index: 1296767 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1124. Min Act: -0.1700

Data Index: 782064 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1436. Min Act: -0.1700

Data Index: 96579 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.2061. Min Act: -0.1700

Data Index: 695970 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1436. Min Act: -0.1700

Data Index: 752635 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1436. Min Act: -0.1700

Data Index: 486239 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1124. Min Act: -0.1700

Data Index: 1197987 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.0186. Min Act: -0.1700

Data Index: 907609 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1124. Min Act: -0.1700

Data Index: 778751 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1124. Min Act: -0.1700

Data Index: 530516 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.1124. Min Act: -0.1700

Data Index: 1321192 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 5.3311. Min Range: -5.3311

Max Act: 5.0499. Min Act: -0.1700

Data Index: 172038 (C4 (Web Text))

Max Activating Token Index: 586