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

Dataset: Open Web Text

Neuron 1184 in Layer 4

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: 3.8670. Min Range: -3.8670

Max Act: 3.8670. Min Act: -0.1700

Data Index: 6133703 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7643. Min Act: -0.1700

Data Index: 702903 (Open Web Text)

Max Activating Token Index: 266

Text #2

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7294. Min Act: -0.1700

Data Index: 5033663 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6851. Min Act: -0.1700

Data Index: 7146484 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7175. Min Act: -0.1700

Data Index: 6579960 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7205. Min Act: -0.1700

Data Index: 1904082 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6554. Min Act: -0.1700

Data Index: 2902090 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6912. Min Act: -0.1700

Data Index: 1259461 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6586. Min Act: -0.1700

Data Index: 7614102 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6731. Min Act: -0.1700

Data Index: 1973641 (Open Web Text)

Max Activating Token Index: 267

Text #10

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6665. Min Act: -0.1700

Data Index: 4907684 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.5981. Min Act: -0.1700

Data Index: 4774501 (Open Web Text)

Max Activating Token Index: 488

Text #12

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6063. Min Act: -0.1700

Data Index: 7603576 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6268. Min Act: -0.1700

Data Index: 7112821 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.5937. Min Act: -0.1700

Data Index: 1385618 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6034. Min Act: -0.1700

Data Index: 4352430 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6195. Min Act: -0.1700

Data Index: 3440228 (Open Web Text)

Max Activating Token Index: 805

Text #17

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.5950. Min Act: -0.1700

Data Index: 7019151 (Open Web Text)

Max Activating Token Index: 171

Text #18

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.5697. Min Act: -0.1700

Data Index: 7138048 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6133. Min Act: -0.1700

Data Index: 8221562 (Open Web Text)

Max Activating Token Index: 838