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

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

Neuron 650 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1796. Min Act: -0.1700

Data Index: 1357685 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1484. Min Act: -0.1700

Data Index: 1179075 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1796. Min Act: -0.1700

Data Index: 1252458 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1171. Min Act: -0.1700

Data Index: 209061 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0859. Min Act: -0.1700

Data Index: 525214 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1484. Min Act: -0.1700

Data Index: 1043398 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0546. Min Act: -0.1700

Data Index: 70476 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1171. Min Act: -0.1700

Data Index: 478092 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1171. Min Act: -0.1700

Data Index: 1318622 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0859. Min Act: -0.1700

Data Index: 630243 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.1171. Min Act: -0.1700

Data Index: 1008791 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0546. Min Act: -0.1700

Data Index: 661553 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0859. Min Act: -0.1700

Data Index: 1121000 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0546. Min Act: -0.1700

Data Index: 976067 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 5.1796. Min Range: -5.1796

Max Act: 4.9921. Min Act: -0.1700

Data Index: 958209 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0234. Min Act: -0.1700

Data Index: 566613 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0546. Min Act: -0.1700

Data Index: 1153642 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0859. Min Act: -0.1700

Data Index: 1120940 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 5.1796. Min Range: -5.1796

Max Act: 5.0234. Min Act: -0.1700

Data Index: 1058718 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 5.1796. Min Range: -5.1796

Max Act: 4.9921. Min Act: -0.1700

Data Index: 104804 (C4 (Web Text))

Max Activating Token Index: 144