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

Dataset: Open Web Text

Neuron 2320 in Layer 2

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: 4.3474. Min Range: -4.3474

Max Act: 4.3474. Min Act: -0.1700

Data Index: 164255 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.3126. Min Act: -0.1700

Data Index: 5302298 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2849. Min Act: -0.1700

Data Index: 3343361 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2865. Min Act: -0.1700

Data Index: 5401973 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2690. Min Act: -0.1700

Data Index: 2410648 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.3037. Min Act: -0.1700

Data Index: 2410653 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2832. Min Act: -0.1700

Data Index: 2410645 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2957. Min Act: -0.1700

Data Index: 2310470 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.3111. Min Act: -0.1700

Data Index: 5075926 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2990. Min Act: -0.1700

Data Index: 6919353 (Open Web Text)

Max Activating Token Index: 586

Text #10

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2776. Min Act: -0.1700

Data Index: 5842809 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2870. Min Act: -0.1700

Data Index: 3994230 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2730. Min Act: -0.1700

Data Index: 3059519 (Open Web Text)

Max Activating Token Index: 239

Text #13

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2575. Min Act: -0.1700

Data Index: 4674522 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2486. Min Act: -0.1700

Data Index: 2034810 (Open Web Text)

Max Activating Token Index: 280

Text #15

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2669. Min Act: -0.1700

Data Index: 498365 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2630. Min Act: -0.1700

Data Index: 1287339 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2490. Min Act: -0.1700

Data Index: 1813721 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2626. Min Act: -0.1700

Data Index: 5319650 (Open Web Text)

Max Activating Token Index: 991

Text #19

Max Range: 4.3474. Min Range: -4.3474

Max Act: 4.2520. Min Act: -0.1700

Data Index: 5392008 (Open Web Text)

Max Activating Token Index: 606