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

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

Neuron 1563 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: 4.0288. Min Range: -4.0288

Max Act: 4.0288. Min Act: -0.1700

Data Index: 205438 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.9268. Min Act: -0.1700

Data Index: 320860 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.8634. Min Act: -0.1700

Data Index: 46164 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.8633. Min Act: -0.1700

Data Index: 327765 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.8415. Min Act: -0.1700

Data Index: 1090474 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.8193. Min Act: -0.1700

Data Index: 576682 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.8008. Min Act: -0.1700

Data Index: 1105916 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.8000. Min Act: -0.1700

Data Index: 587990 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7886. Min Act: -0.1700

Data Index: 937730 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7823. Min Act: -0.1700

Data Index: 1242008 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7878. Min Act: -0.1700

Data Index: 540007 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7816. Min Act: -0.1700

Data Index: 820697 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7810. Min Act: -0.1700

Data Index: 1340331 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7923. Min Act: -0.1700

Data Index: 868936 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7671. Min Act: -0.1700

Data Index: 1001344 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7638. Min Act: -0.1700

Data Index: 514050 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7548. Min Act: -0.1700

Data Index: 1327820 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7448. Min Act: -0.1700

Data Index: 747579 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7508. Min Act: -0.1700

Data Index: 1128059 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.7608. Min Act: -0.1700

Data Index: 374805 (C4 (Web Text))

Max Activating Token Index: 213