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

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

Neuron 1879 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: 3.3524. Min Range: -3.3524

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1242336 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.3403. Min Act: -0.1700

Data Index: 915171 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2997. Min Act: -0.1700

Data Index: 227717 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2927. Min Act: -0.1700

Data Index: 1162802 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2765. Min Act: -0.1700

Data Index: 1200680 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2745. Min Act: -0.1700

Data Index: 1124167 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2454. Min Act: -0.1700

Data Index: 99754 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2339. Min Act: -0.1700

Data Index: 94708 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2532. Min Act: -0.1700

Data Index: 129936 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2532. Min Act: -0.1700

Data Index: 885122 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2543. Min Act: -0.1700

Data Index: 707984 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2545. Min Act: -0.1700

Data Index: 9455 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2148. Min Act: -0.1699

Data Index: 558739 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2225. Min Act: -0.1700

Data Index: 140487 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.1936. Min Act: -0.1700

Data Index: 1349546 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.1988. Min Act: -0.1700

Data Index: 371513 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2034. Min Act: -0.1700

Data Index: 209677 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2203. Min Act: -0.1700

Data Index: 1211452 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1146885 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.3524. Min Range: -3.3524

Max Act: 3.2171. Min Act: -0.1700

Data Index: 192902 (C4 (Web Text))

Max Activating Token Index: 375