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

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

Neuron 1336 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3245. Min Range: -5.3245

Max Act: 5.3245. Min Act: -0.1700

Data Index: 454420 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 5.3245. Min Range: -5.3245

Max Act: 5.1682. Min Act: -0.1700

Data Index: 324981 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 5.3245. Min Range: -5.3245

Max Act: 5.0745. Min Act: -0.1700

Data Index: 626076 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 5.3245. Min Range: -5.3245

Max Act: 5.0745. Min Act: -0.1700

Data Index: 683654 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9807. Min Act: -0.1700

Data Index: 222463 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9807. Min Act: -0.1700

Data Index: 1295128 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 5.3245. Min Range: -5.3245

Max Act: 5.0120. Min Act: -0.1700

Data Index: 1327729 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9495. Min Act: -0.1700

Data Index: 27716 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 5.3245. Min Range: -5.3245

Max Act: 5.0120. Min Act: -0.1700

Data Index: 1031715 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9495. Min Act: -0.1700

Data Index: 711903 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9495. Min Act: -0.1700

Data Index: 446289 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9807. Min Act: -0.1700

Data Index: 717547 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8870. Min Act: -0.1700

Data Index: 56532 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8870. Min Act: -0.1700

Data Index: 491812 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.9495. Min Act: -0.1700

Data Index: 408267 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8870. Min Act: -0.1700

Data Index: 571799 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8870. Min Act: -0.1700

Data Index: 1185294 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8245. Min Act: -0.1700

Data Index: 1255595 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8557. Min Act: -0.1700

Data Index: 474485 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 5.3245. Min Range: -5.3245

Max Act: 4.8557. Min Act: -0.1700

Data Index: 395582 (C4 (Web Text))

Max Activating Token Index: 917