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

Dataset: Open Web Text

Neuron 1312 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: 3.2863. Min Range: -3.2863

Max Act: 3.2863. Min Act: -0.1700

Data Index: 6372460 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.2295. Min Act: -0.1700

Data Index: 922712 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.2015. Min Act: -0.1700

Data Index: 2294211 (Open Web Text)

Max Activating Token Index: 810

Text #3

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1593. Min Act: -0.1700

Data Index: 7588129 (Open Web Text)

Max Activating Token Index: 1001

Text #4

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1896. Min Act: -0.1700

Data Index: 6644132 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1702. Min Act: -0.1700

Data Index: 3565551 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1599. Min Act: -0.1700

Data Index: 5647447 (Open Web Text)

Max Activating Token Index: 171

Text #7

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1598. Min Act: -0.1700

Data Index: 7888268 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1242. Min Act: -0.1700

Data Index: 2905930 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1441. Min Act: -0.1700

Data Index: 5472742 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1270. Min Act: -0.1700

Data Index: 5421916 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1624. Min Act: -0.1700

Data Index: 3247439 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1413. Min Act: -0.1700

Data Index: 5253925 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1490. Min Act: -0.1700

Data Index: 5133332 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1266. Min Act: -0.1700

Data Index: 5791670 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.0921. Min Act: -0.1700

Data Index: 2502783 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1170. Min Act: -0.1700

Data Index: 423051 (Open Web Text)

Max Activating Token Index: 463

Text #17

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1122. Min Act: -0.1700

Data Index: 4704443 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.1033. Min Act: -0.1700

Data Index: 7338136 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 3.2863. Min Range: -3.2863

Max Act: 3.0768. Min Act: -0.1700

Data Index: 7269320 (Open Web Text)

Max Activating Token Index: 367