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

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

Neuron 1874 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: 3.1802. Min Range: -3.1802

Max Act: 3.1802. Min Act: -0.1696

Data Index: 489434 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0188. Min Act: -0.1700

Data Index: 48408 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9979. Min Act: -0.1700

Data Index: 1213428 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9540. Min Act: -0.1700

Data Index: 1340163 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9599. Min Act: -0.1700

Data Index: 371477 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9399. Min Act: -0.1699

Data Index: 132577 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9434. Min Act: -0.1700

Data Index: 52624 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9404. Min Act: -0.1700

Data Index: 252195 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9156. Min Act: -0.1700

Data Index: 514920 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9213. Min Act: -0.1700

Data Index: 1121586 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9324. Min Act: -0.1700

Data Index: 1241101 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9182. Min Act: -0.1700

Data Index: 578135 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9224. Min Act: -0.1700

Data Index: 445970 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9076. Min Act: -0.1700

Data Index: 819126 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8878. Min Act: -0.1700

Data Index: 534292 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8794. Min Act: -0.1700

Data Index: 656577 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8922. Min Act: -0.1700

Data Index: 742064 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8949. Min Act: -0.1700

Data Index: 1198811 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8848. Min Act: -0.1700

Data Index: 1033365 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8775. Min Act: -0.1698

Data Index: 672407 (C4 (Web Text))

Max Activating Token Index: 159