Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 932 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.9105. Min Act: -0.1700

Data Index: 444639 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8356. Min Act: -0.1700

Data Index: 4283132 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6728. Min Act: -0.1700

Data Index: 6581851 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6871. Min Act: -0.1700

Data Index: 8349998 (Open Web Text)

Max Activating Token Index: 496

Text #4

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7192. Min Act: -0.1700

Data Index: 3270402 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7220. Min Act: -0.1700

Data Index: 4458950 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6427. Min Act: -0.1700

Data Index: 288898 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6712. Min Act: -0.1700

Data Index: 4058865 (Open Web Text)

Max Activating Token Index: 145

Text #8

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6784. Min Act: -0.1700

Data Index: 4452634 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6565. Min Act: -0.1700

Data Index: 1518242 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6565. Min Act: -0.1700

Data Index: 8162573 (Open Web Text)

Max Activating Token Index: 292

Text #11

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6613. Min Act: -0.1700

Data Index: 6248978 (Open Web Text)

Max Activating Token Index: 368

Text #12

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6669. Min Act: -0.1700

Data Index: 3298779 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6445. Min Act: -0.1700

Data Index: 2620208 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6288. Min Act: -0.1700

Data Index: 444637 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6418. Min Act: -0.1700

Data Index: 6181896 (Open Web Text)

Max Activating Token Index: 61

Text #16

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5868. Min Act: -0.1700

Data Index: 5359608 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5842. Min Act: -0.1700

Data Index: 7712524 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5588. Min Act: -0.1700

Data Index: 3469272 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5617. Min Act: -0.1700

Data Index: 1631559 (Open Web Text)

Max Activating Token Index: 5