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

Dataset: Open Web Text

Neuron 2559 in Layer 0

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: 4.9085. Min Range: -4.9085

Max Act: 4.8973. Min Act: -0.1700

Data Index: 6034065 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8931. Min Act: -0.1700

Data Index: 5117452 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.9085. Min Act: -0.1700

Data Index: 5724164 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8564. Min Act: -0.1700

Data Index: 2508443 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8557. Min Act: -0.1700

Data Index: 3253773 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8679. Min Act: -0.1700

Data Index: 6401037 (Open Web Text)

Max Activating Token Index: 680

Text #6

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8670. Min Act: -0.1700

Data Index: 3944114 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8455. Min Act: -0.1700

Data Index: 3978907 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8263. Min Act: -0.1700

Data Index: 8758378 (Open Web Text)

Max Activating Token Index: 746

Text #9

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8188. Min Act: -0.1700

Data Index: 8447585 (Open Web Text)

Max Activating Token Index: 841

Text #10

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8505. Min Act: -0.1700

Data Index: 7918367 (Open Web Text)

Max Activating Token Index: 125

Text #11

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.7973. Min Act: -0.1700

Data Index: 7284430 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8138. Min Act: -0.1700

Data Index: 1349190 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8236. Min Act: -0.1700

Data Index: 202366 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8201. Min Act: -0.1700

Data Index: 6740529 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8351. Min Act: -0.1700

Data Index: 6624397 (Open Web Text)

Max Activating Token Index: 597

Text #16

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8336. Min Act: -0.1700

Data Index: 2183116 (Open Web Text)

Max Activating Token Index: 673

Text #17

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8186. Min Act: -0.1700

Data Index: 6160412 (Open Web Text)

Max Activating Token Index: 484

Text #18

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.8243. Min Act: -0.1700

Data Index: 3456516 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 4.9085. Min Range: -4.9085

Max Act: 4.7995. Min Act: -0.1700

Data Index: 5183332 (Open Web Text)

Max Activating Token Index: 227