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

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

Neuron 277 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: 3.6198. Min Range: -3.6198

Max Act: 3.6138. Min Act: -0.1700

Data Index: 1328184 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.6198. Min Act: -0.1700

Data Index: 641594 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5396. Min Act: -0.1700

Data Index: 1350952 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5521. Min Act: -0.1700

Data Index: 691013 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5267. Min Act: -0.1700

Data Index: 678700 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5310. Min Act: -0.1700

Data Index: 309554 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5266. Min Act: -0.1700

Data Index: 1236029 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5066. Min Act: -0.1700

Data Index: 351343 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5152. Min Act: -0.1700

Data Index: 443654 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5033. Min Act: -0.1700

Data Index: 235018 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5007. Min Act: -0.1700

Data Index: 997673 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4902. Min Act: -0.1700

Data Index: 593317 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4939. Min Act: -0.1700

Data Index: 1244366 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4916. Min Act: -0.1700

Data Index: 23487 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4736. Min Act: -0.1700

Data Index: 1214096 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4741. Min Act: -0.1700

Data Index: 814207 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4688. Min Act: -0.1700

Data Index: 782930 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1030294 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4500. Min Act: -0.1700

Data Index: 672604 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4464. Min Act: -0.1700

Data Index: 831224 (C4 (Web Text))

Max Activating Token Index: 99