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

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

Neuron 532 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: 3.6897. Min Range: -3.6897

Max Act: 3.6897. Min Act: -0.1700

Data Index: 36758 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5874. Min Act: -0.1700

Data Index: 1097587 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1188029 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5865. Min Act: -0.1700

Data Index: 237235 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5643. Min Act: -0.1700

Data Index: 1119037 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5274. Min Act: -0.1700

Data Index: 1338411 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5052. Min Act: -0.1700

Data Index: 729290 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5664. Min Act: -0.1700

Data Index: 500653 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1207262 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5176. Min Act: -0.1700

Data Index: 984963 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5194. Min Act: -0.1700

Data Index: 749564 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4863. Min Act: -0.1700

Data Index: 582267 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4777. Min Act: -0.1700

Data Index: 366773 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4617. Min Act: -0.1700

Data Index: 992939 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5088. Min Act: -0.1700

Data Index: 64206 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4490. Min Act: -0.1700

Data Index: 168807 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4463. Min Act: -0.1700

Data Index: 209548 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4253. Min Act: -0.1700

Data Index: 387419 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4192. Min Act: -0.1700

Data Index: 1197807 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4704. Min Act: -0.1700

Data Index: 179068 (C4 (Web Text))

Max Activating Token Index: 567