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

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

Neuron 109 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9693. Min Act: -0.1700

Data Index: 240419 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9693. Min Act: -0.1700

Data Index: 865801 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8755. Min Act: -0.1700

Data Index: 432251 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8755. Min Act: -0.1700

Data Index: 174914 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8442. Min Act: -0.1700

Data Index: 1068647 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8442. Min Act: -0.1700

Data Index: 1123805 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8130. Min Act: -0.1700

Data Index: 465673 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7817. Min Act: -0.1700

Data Index: 955897 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7504. Min Act: -0.1700

Data Index: 822127 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7191. Min Act: -0.1700

Data Index: 62028 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7817. Min Act: -0.1700

Data Index: 925717 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6878. Min Act: -0.1700

Data Index: 289101 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6565. Min Act: -0.1700

Data Index: 1331740 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6565. Min Act: -0.1700

Data Index: 492328 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7191. Min Act: -0.1700

Data Index: 32570 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6878. Min Act: -0.1700

Data Index: 904286 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6878. Min Act: -0.1700

Data Index: 347094 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6565. Min Act: -0.1700

Data Index: 568742 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6252. Min Act: -0.1700

Data Index: 70265 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.6565. Min Act: -0.1700

Data Index: 952016 (C4 (Web Text))

Max Activating Token Index: 472