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

Dataset: Open Web Text

Neuron 1058 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: 4.7229. Min Range: -4.7229

Max Act: 4.7216. Min Act: -0.1700

Data Index: 7463160 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.7229. Min Act: -0.1700

Data Index: 1966484 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.5281. Min Act: -0.1700

Data Index: 8224673 (Open Web Text)

Max Activating Token Index: 817

Text #3

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.5668. Min Act: -0.1700

Data Index: 2867359 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4746. Min Act: -0.1700

Data Index: 5683771 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.5325. Min Act: -0.1700

Data Index: 1784515 (Open Web Text)

Max Activating Token Index: 187

Text #6

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4995. Min Act: -0.1700

Data Index: 3288462 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4620. Min Act: -0.1700

Data Index: 6512312 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4967. Min Act: -0.1700

Data Index: 5506698 (Open Web Text)

Max Activating Token Index: 212

Text #9

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4882. Min Act: -0.1700

Data Index: 8010220 (Open Web Text)

Max Activating Token Index: 831

Text #10

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4482. Min Act: -0.1700

Data Index: 4777645 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4462. Min Act: -0.1700

Data Index: 4282269 (Open Web Text)

Max Activating Token Index: 526

Text #12

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4753. Min Act: -0.1700

Data Index: 4122892 (Open Web Text)

Max Activating Token Index: 143

Text #13

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4421. Min Act: -0.1700

Data Index: 341775 (Open Web Text)

Max Activating Token Index: 845

Text #14

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4467. Min Act: -0.1700

Data Index: 2379638 (Open Web Text)

Max Activating Token Index: 1000

Text #15

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4139. Min Act: -0.1700

Data Index: 5082026 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4034. Min Act: -0.1700

Data Index: 4363611 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4167. Min Act: -0.1700

Data Index: 4802681 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4044. Min Act: -0.1700

Data Index: 2439673 (Open Web Text)

Max Activating Token Index: 234

Text #19

Max Range: 4.7229. Min Range: -4.7229

Max Act: 4.4230. Min Act: -0.1700

Data Index: 3897417 (Open Web Text)

Max Activating Token Index: 652