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

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

Neuron 1013 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: 3.2814. Min Range: -3.2814

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1159902 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.2537. Min Act: -0.1699

Data Index: 685416 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.2210. Min Act: -0.1700

Data Index: 917108 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.2258. Min Act: -0.1699

Data Index: 175362 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.2230. Min Act: -0.1699

Data Index: 304765 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1684. Min Act: -0.1700

Data Index: 557866 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1694. Min Act: -0.1698

Data Index: 58676 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1654. Min Act: -0.1700

Data Index: 1341453 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1592. Min Act: -0.1700

Data Index: 1098121 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1411. Min Act: -0.1700

Data Index: 1119585 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1487. Min Act: -0.1700

Data Index: 125245 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1495. Min Act: -0.1700

Data Index: 770386 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1307. Min Act: -0.1700

Data Index: 428904 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1333. Min Act: -0.1699

Data Index: 290795 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1391. Min Act: -0.1700

Data Index: 345102 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1473. Min Act: -0.1700

Data Index: 776228 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1117. Min Act: -0.1700

Data Index: 176953 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1284. Min Act: -0.1699

Data Index: 623153 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1310. Min Act: -0.1699

Data Index: 1264317 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 3.2814. Min Range: -3.2814

Max Act: 3.1133. Min Act: -0.1700

Data Index: 538773 (C4 (Web Text))

Max Activating Token Index: 905