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

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

Neuron 1713 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: 6.0516. Min Range: -6.0516

Max Act: 6.0516. Min Act: -0.1700

Data Index: 636560 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.8418. Min Act: -0.1700

Data Index: 161653 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.8024. Min Act: -0.1700

Data Index: 1579452 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.7625. Min Act: -0.1700

Data Index: 463915 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.5966. Min Act: -0.1700

Data Index: 447878 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.5160. Min Act: -0.1700

Data Index: 283146 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.4648. Min Act: -0.1700

Data Index: 733059 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3855. Min Act: -0.1700

Data Index: 1630695 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3523. Min Act: -0.1700

Data Index: 454175 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3808. Min Act: -0.1700

Data Index: 1199917 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3138. Min Act: -0.1700

Data Index: 1007341 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3362. Min Act: -0.1700

Data Index: 426105 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3267. Min Act: -0.1700

Data Index: 377732 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.2390. Min Act: -0.1700

Data Index: 867077 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.3368. Min Act: -0.1700

Data Index: 872289 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.2051. Min Act: -0.1700

Data Index: 734980 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.2518. Min Act: -0.1700

Data Index: 155054 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.2087. Min Act: -0.1700

Data Index: 182684 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.1835. Min Act: -0.1700

Data Index: 977021 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 6.0516. Min Range: -6.0516

Max Act: 5.1920. Min Act: -0.1700

Data Index: 1221959 (C4 (Web Text))

Max Activating Token Index: 18