Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 371 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5947. Min Act: -0.1700

Data Index: 267933 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5941. Min Act: -0.1700

Data Index: 302926 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5884. Min Act: -0.1700

Data Index: 943637 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5700. Min Act: -0.1700

Data Index: 1049137 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5658. Min Act: -0.1700

Data Index: 545101 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5312. Min Act: -0.1700

Data Index: 1125764 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5000. Min Act: -0.1700

Data Index: 332253 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.5137. Min Act: -0.1700

Data Index: 699609 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4893. Min Act: -0.1700

Data Index: 155119 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4804. Min Act: -0.1700

Data Index: 182463 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4624. Min Act: -0.1700

Data Index: 83137 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4740. Min Act: -0.1700

Data Index: 537768 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4550. Min Act: -0.1700

Data Index: 139930 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4649. Min Act: -0.1700

Data Index: 410663 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4375. Min Act: -0.1700

Data Index: 610152 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4347. Min Act: -0.1700

Data Index: 957182 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4479. Min Act: -0.1700

Data Index: 39813 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4427. Min Act: -0.1700

Data Index: 314260 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4318. Min Act: -0.1700

Data Index: 1239532 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 3.5947. Min Range: -3.5947

Max Act: 3.4186. Min Act: -0.1700

Data Index: 991944 (C4 (Web Text))

Max Activating Token Index: 894