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

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

Neuron 1436 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: 5.7315. Min Range: -5.7315

Max Act: 5.7315. Min Act: -0.1700

Data Index: 172001 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.6690. Min Act: -0.1700

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.7003. Min Act: -0.1700

Data Index: 306022 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.4190. Min Act: -0.1700

Data Index: 714559 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.4815. Min Act: -0.1700

Data Index: 535998 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.4815. Min Act: -0.1700

Data Index: 62899 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.5128. Min Act: -0.1700

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.5128. Min Act: -0.1700

Data Index: 328157 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.4815. Min Act: -0.1700

Data Index: 1069834 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.5128. Min Act: -0.1700

Data Index: 1187021 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.3565. Min Act: -0.1700

Data Index: 1129560 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.3253. Min Act: -0.1700

Data Index: 382063 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.3253. Min Act: -0.1700

Data Index: 71091 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.3565. Min Act: -0.1700

Data Index: 815132 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.4190. Min Act: -0.1700

Data Index: 1213002 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.3878. Min Act: -0.1700

Data Index: 854616 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.4190. Min Act: -0.1700

Data Index: 669956 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.3253. Min Act: -0.1700

Data Index: 1312578 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.1690. Min Act: -0.1700

Data Index: 521770 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 5.7315. Min Range: -5.7315

Max Act: 5.1378. Min Act: -0.1700

Data Index: 81278 (C4 (Web Text))

Max Activating Token Index: 314