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

Dataset: Open Web Text

Neuron 2864 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: 5.8852. Min Range: -5.8852

Max Act: 5.8852. Min Act: -0.1700

Data Index: 5552483 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.7865. Min Act: -0.1700

Data Index: 5387451 (Open Web Text)

Max Activating Token Index: 311

Text #2

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.7159. Min Act: -0.1700

Data Index: 8832150 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.6327. Min Act: -0.1700

Data Index: 214514 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.6004. Min Act: -0.1700

Data Index: 2759939 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.5530. Min Act: -0.1700

Data Index: 5176927 (Open Web Text)

Max Activating Token Index: 94

Text #6

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4466. Min Act: -0.1700

Data Index: 3879998 (Open Web Text)

Max Activating Token Index: 516

Text #7

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4773. Min Act: -0.1700

Data Index: 2004786 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4368. Min Act: -0.1700

Data Index: 2828063 (Open Web Text)

Max Activating Token Index: 937

Text #9

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4325. Min Act: -0.1700

Data Index: 8531750 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4053. Min Act: -0.1700

Data Index: 119072 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4236. Min Act: -0.1700

Data Index: 4293779 (Open Web Text)

Max Activating Token Index: 259

Text #12

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4563. Min Act: -0.1700

Data Index: 7021211 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4638. Min Act: -0.1700

Data Index: 4074448 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4515. Min Act: -0.1700

Data Index: 4540507 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.3594. Min Act: -0.1700

Data Index: 7535341 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4189. Min Act: -0.1700

Data Index: 876005 (Open Web Text)

Max Activating Token Index: 663

Text #17

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.3893. Min Act: -0.1700

Data Index: 2048160 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4089. Min Act: -0.1700

Data Index: 6623697 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 5.8852. Min Range: -5.8852

Max Act: 5.4058. Min Act: -0.1700

Data Index: 2757464 (Open Web Text)

Max Activating Token Index: 403