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

Dataset: Open Web Text

Neuron 824 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: 3.5903. Min Range: -3.5903

Max Act: 3.5903. Min Act: -0.1700

Data Index: 7325498 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.5441. Min Act: -0.1700

Data Index: 4547301 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.5236. Min Act: -0.1700

Data Index: 7761227 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4934. Min Act: -0.1700

Data Index: 1987339 (Open Web Text)

Max Activating Token Index: 322

Text #4

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4568. Min Act: -0.1700

Data Index: 5249061 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4133. Min Act: -0.1700

Data Index: 1392950 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4638. Min Act: -0.1700

Data Index: 6895808 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4352. Min Act: -0.1700

Data Index: 453163 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4550. Min Act: -0.1700

Data Index: 3941875 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4184. Min Act: -0.1700

Data Index: 4018476 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4048. Min Act: -0.1700

Data Index: 1672735 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4376. Min Act: -0.1700

Data Index: 3465049 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4199. Min Act: -0.1700

Data Index: 6052384 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4234. Min Act: -0.1700

Data Index: 902011 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4280. Min Act: -0.1700

Data Index: 7464235 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4218. Min Act: -0.1700

Data Index: 2741057 (Open Web Text)

Max Activating Token Index: 304

Text #16

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4066. Min Act: -0.1700

Data Index: 3005284 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4017. Min Act: -0.1700

Data Index: 6143879 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.3821. Min Act: -0.1700

Data Index: 518061 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 3.5903. Min Range: -3.5903

Max Act: 3.4179. Min Act: -0.1700

Data Index: 2403972 (Open Web Text)

Max Activating Token Index: 255