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

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

Neuron 213 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: 3.7859. Min Range: -3.7859

Max Act: 3.7859. Min Act: -0.1700

Data Index: 147906 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.7182. Min Act: -0.1700

Data Index: 186593 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.7079. Min Act: -0.1700

Data Index: 415076 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6309. Min Act: -0.1700

Data Index: 511047 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6235. Min Act: -0.1700

Data Index: 1147328 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5965. Min Act: -0.1700

Data Index: 155098 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5995. Min Act: -0.1700

Data Index: 7568 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6052. Min Act: -0.1700

Data Index: 1206006 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6589. Min Act: -0.1700

Data Index: 217230 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6034. Min Act: -0.1700

Data Index: 155486 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5388. Min Act: -0.1700

Data Index: 711810 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5990. Min Act: -0.1700

Data Index: 144696 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6120. Min Act: -0.1700

Data Index: 1315703 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5597. Min Act: -0.1700

Data Index: 583890 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5675. Min Act: -0.1700

Data Index: 1261675 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.6050. Min Act: -0.1700

Data Index: 1237710 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5578. Min Act: -0.1700

Data Index: 923540 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5466. Min Act: -0.1700

Data Index: 1355993 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5362. Min Act: -0.1700

Data Index: 644707 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.5722. Min Act: -0.1700

Data Index: 423030 (C4 (Web Text))

Max Activating Token Index: 277