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

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

Neuron 886 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: 3.4191. Min Range: -3.4191

Max Act: 3.4191. Min Act: -0.1700

Data Index: 79418 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3720. Min Act: -0.1700

Data Index: 1140164 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3407. Min Act: -0.1700

Data Index: 942247 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3563. Min Act: -0.1700

Data Index: 41018 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3250. Min Act: -0.1700

Data Index: 854260 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2935. Min Act: -0.1700

Data Index: 115669 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3250. Min Act: -0.1700

Data Index: 946558 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2935. Min Act: -0.1700

Data Index: 164477 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3093. Min Act: -0.1700

Data Index: 971839 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2935. Min Act: -0.1700

Data Index: 927506 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2464. Min Act: -0.1700

Data Index: 1220784 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3093. Min Act: -0.1700

Data Index: 1039310 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2621. Min Act: -0.1700

Data Index: 435560 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2464. Min Act: -0.1700

Data Index: 906655 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2307. Min Act: -0.1700

Data Index: 1252596 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2464. Min Act: -0.1700

Data Index: 575504 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2307. Min Act: -0.1700

Data Index: 1048035 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2621. Min Act: -0.1700

Data Index: 1305180 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2150. Min Act: -0.1700

Data Index: 192781 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2150. Min Act: -0.1700

Data Index: 925134 (C4 (Web Text))

Max Activating Token Index: 913