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

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

Neuron 1419 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: 5.1325. Min Range: -5.1325

Max Act: 5.1325. Min Act: -0.1700

Data Index: 686609 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.1013. Min Act: -0.1700

Data Index: 606323 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.0700. Min Act: -0.1700

Data Index: 32739 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.0075. Min Act: -0.1700

Data Index: 627095 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1089228 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.0388. Min Act: -0.1700

Data Index: 1022102 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9763. Min Act: -0.1700

Data Index: 1231937 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1219811 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 5.1325. Min Range: -5.1325

Max Act: 5.0075. Min Act: -0.1700

Data Index: 215470 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1281479 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9450. Min Act: -0.1700

Data Index: 196210 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9763. Min Act: -0.1700

Data Index: 1340720 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1200870 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.8513. Min Act: -0.1699

Data Index: 60580 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1129769 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.9138. Min Act: -0.1700

Data Index: 857714 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.7888. Min Act: -0.1700

Data Index: 440013 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.8200. Min Act: -0.1700

Data Index: 298086 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.8200. Min Act: -0.1700

Data Index: 1147795 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 5.1325. Min Range: -5.1325

Max Act: 4.7888. Min Act: -0.1700

Data Index: 977143 (C4 (Web Text))

Max Activating Token Index: 853