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

Dataset: Open Web Text

Neuron 1823 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: 3.6988. Min Range: -3.6988

Max Act: 3.6988. Min Act: -0.1700

Data Index: 1355032 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6200. Min Act: -0.1700

Data Index: 1112604 (Open Web Text)

Max Activating Token Index: 244

Text #2

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5011. Min Act: -0.1700

Data Index: 8757605 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5224. Min Act: -0.1700

Data Index: 177417 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4461. Min Act: -0.1700

Data Index: 421398 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4509. Min Act: -0.1700

Data Index: 8479686 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4573. Min Act: -0.1700

Data Index: 605658 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4558. Min Act: -0.1700

Data Index: 1669894 (Open Web Text)

Max Activating Token Index: 583

Text #8

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4100. Min Act: -0.1700

Data Index: 8305977 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4291. Min Act: -0.1700

Data Index: 451397 (Open Web Text)

Max Activating Token Index: 342

Text #10

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3422. Min Act: -0.1700

Data Index: 5858545 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4071. Min Act: -0.1700

Data Index: 6615613 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3815. Min Act: -0.1700

Data Index: 6982834 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4058. Min Act: -0.1700

Data Index: 8757606 (Open Web Text)

Max Activating Token Index: 448

Text #14

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3768. Min Act: -0.1700

Data Index: 7554153 (Open Web Text)

Max Activating Token Index: 746

Text #15

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3875. Min Act: -0.1700

Data Index: 421397 (Open Web Text)

Max Activating Token Index: 492

Text #16

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4047. Min Act: -0.1700

Data Index: 633929 (Open Web Text)

Max Activating Token Index: 551

Text #17

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.4145. Min Act: -0.1700

Data Index: 8350577 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3328. Min Act: -0.1700

Data Index: 8243459 (Open Web Text)

Max Activating Token Index: 676

Text #19

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3025. Min Act: -0.1700

Data Index: 5147982 (Open Web Text)

Max Activating Token Index: 705