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

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

Neuron 1947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.4932. Min Act: -0.1700

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.3995. Min Act: -0.1700

Data Index: 1043100 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.3370. Min Act: -0.1700

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.2745. Min Act: -0.1700

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.3057. Min Act: -0.1700

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.2120. Min Act: -0.1700

Data Index: 1341459 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.2120. Min Act: -0.1700

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.2432. Min Act: -0.1700

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.0557. Min Act: -0.1700

Data Index: 29251 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.2432. Min Act: -0.1699

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1807. Min Act: -0.1700

Data Index: 1208476 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.2120. Min Act: -0.1700

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1495. Min Act: -0.1700

Data Index: 1208968 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1495. Min Act: -0.1700

Data Index: 302340 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1495. Min Act: -0.1700

Data Index: 732017 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1182. Min Act: -0.1700

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.0870. Min Act: -0.1700

Data Index: 1084998 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1182. Min Act: -0.1700

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.1495. Min Act: -0.1700

Data Index: 878003 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 5.4932. Min Range: -5.4932

Max Act: 5.0870. Min Act: -0.1700

Data Index: 906941 (C4 (Web Text))

Max Activating Token Index: 161