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

Dataset: Open Web Text

Neuron 848 in Layer 5

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: 3.1951. Min Range: -3.1951

Max Act: 3.1951. Min Act: -0.1700

Data Index: 4712244 (Open Web Text)

Max Activating Token Index: 917

Text #1

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.0358. Min Act: -0.1700

Data Index: 4713870 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.0125. Min Act: -0.1700

Data Index: 2243299 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 3.1951. Min Range: -3.1951

Max Act: 3.0181. Min Act: -0.1700

Data Index: 1396261 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9754. Min Act: -0.1700

Data Index: 156571 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9750. Min Act: -0.1700

Data Index: 5553558 (Open Web Text)

Max Activating Token Index: 514

Text #6

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9921. Min Act: -0.1700

Data Index: 2228829 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9602. Min Act: -0.1700

Data Index: 8385215 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9646. Min Act: -0.1700

Data Index: 3717124 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9702. Min Act: -0.1700

Data Index: 6571775 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9394. Min Act: -0.1700

Data Index: 1752624 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9175. Min Act: -0.1700

Data Index: 6577298 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9037. Min Act: -0.1700

Data Index: 1311449 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8919. Min Act: -0.1700

Data Index: 6411191 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9212. Min Act: -0.1700

Data Index: 1882230 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9420. Min Act: -0.1700

Data Index: 6219411 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8861. Min Act: -0.1700

Data Index: 5634690 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.9042. Min Act: -0.1700

Data Index: 2264839 (Open Web Text)

Max Activating Token Index: 493

Text #18

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8958. Min Act: -0.1700

Data Index: 6738809 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 3.1951. Min Range: -3.1951

Max Act: 2.8659. Min Act: -0.1700

Data Index: 7706522 (Open Web Text)

Max Activating Token Index: 509