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

Dataset: Open Web Text

Neuron 516 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: 3.6167. Min Range: -3.6167

Max Act: 3.6097. Min Act: -0.1700

Data Index: 6474322 (Open Web Text)

Max Activating Token Index: 820

Text #1

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.6167. Min Act: -0.1700

Data Index: 2589387 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.5255. Min Act: -0.1700

Data Index: 8334261 (Open Web Text)

Max Activating Token Index: 274

Text #3

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4943. Min Act: -0.1700

Data Index: 5234161 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.5135. Min Act: -0.1700

Data Index: 2246968 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4939. Min Act: -0.1700

Data Index: 1179049 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4502. Min Act: -0.1700

Data Index: 8497671 (Open Web Text)

Max Activating Token Index: 496

Text #7

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4688. Min Act: -0.1700

Data Index: 579437 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4954. Min Act: -0.1700

Data Index: 5668604 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4415. Min Act: -0.1700

Data Index: 3806426 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4573. Min Act: -0.1700

Data Index: 2198017 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4937. Min Act: -0.1700

Data Index: 823671 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4347. Min Act: -0.1700

Data Index: 8268643 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4634. Min Act: -0.1700

Data Index: 3275560 (Open Web Text)

Max Activating Token Index: 404

Text #14

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4359. Min Act: -0.1700

Data Index: 5270919 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4470. Min Act: -0.1700

Data Index: 562195 (Open Web Text)

Max Activating Token Index: 926

Text #16

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4406. Min Act: -0.1700

Data Index: 6565727 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4334. Min Act: -0.1700

Data Index: 2356745 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4123. Min Act: -0.1700

Data Index: 3974505 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4759. Min Act: -0.1700

Data Index: 6663143 (Open Web Text)

Max Activating Token Index: 755