Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1696 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2148. Min Range: -3.2148

Max Act: 3.2148. Min Act: -0.1700

Data Index: 196101 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 3.2148. Min Range: -3.2148

Max Act: 3.1203. Min Act: -0.1700

Data Index: 297247 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 3.2148. Min Range: -3.2148

Max Act: 3.0415. Min Act: -0.1700

Data Index: 538654 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 3.2148. Min Range: -3.2148

Max Act: 3.0099. Min Act: -0.1700

Data Index: 927469 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.2148. Min Range: -3.2148

Max Act: 3.0257. Min Act: -0.1700

Data Index: 684925 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9941. Min Act: -0.1700

Data Index: 447322 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9624. Min Act: -0.1700

Data Index: 775922 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9782. Min Act: -0.1700

Data Index: 1212336 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9782. Min Act: -0.1700

Data Index: 1260728 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9624. Min Act: -0.1700

Data Index: 768555 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9624. Min Act: -0.1700

Data Index: 759274 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9466. Min Act: -0.1700

Data Index: 1136640 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9466. Min Act: -0.1700

Data Index: 386358 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9466. Min Act: -0.1700

Data Index: 915319 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9466. Min Act: -0.1700

Data Index: 899711 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9307. Min Act: -0.1700

Data Index: 555282 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9307. Min Act: -0.1700

Data Index: 1209581 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.9149. Min Act: -0.1700

Data Index: 1116231 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.8990. Min Act: -0.1700

Data Index: 398327 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.2148. Min Range: -3.2148

Max Act: 2.8990. Min Act: -0.1700

Data Index: 34033 (C4 (Web Text))

Max Activating Token Index: 978