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

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

Neuron 470 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: 7.4196. Min Range: -7.4196

Max Act: 7.4196. Min Act: -0.1700

Data Index: 1171109 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 7.4196. Min Range: -7.4196

Max Act: 7.1696. Min Act: -0.1700

Data Index: 1101644 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 7.4196. Min Range: -7.4196

Max Act: 7.0446. Min Act: -0.1700

Data Index: 895972 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.9821. Min Act: -0.1700

Data Index: 201117 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.9821. Min Act: -0.1700

Data Index: 372966 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.9196. Min Act: -0.1700

Data Index: 670900 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.9196. Min Act: -0.1700

Data Index: 431401 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.8883. Min Act: -0.1700

Data Index: 71686 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7946. Min Act: -0.1700

Data Index: 376503 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.8258. Min Act: -0.1700

Data Index: 1171552 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7633. Min Act: -0.1700

Data Index: 971643 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7946. Min Act: -0.1700

Data Index: 197720 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7946. Min Act: -0.1700

Data Index: 892130 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7008. Min Act: -0.1700

Data Index: 805897 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7008. Min Act: -0.1700

Data Index: 1078672 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.9508. Min Act: -0.1700

Data Index: 278814 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7633. Min Act: -0.1700

Data Index: 1189934 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7633. Min Act: -0.1700

Data Index: 1308087 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7633. Min Act: -0.1700

Data Index: 242120 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 7.4196. Min Range: -7.4196

Max Act: 6.7321. Min Act: -0.1700

Data Index: 937447 (C4 (Web Text))

Max Activating Token Index: 900