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

Dataset: Open Web Text

Neuron 2720 in Layer 6

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: 3.7375. Min Range: -3.7375

Max Act: 3.7375. Min Act: -0.1700

Data Index: 7257762 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.7134. Min Act: -0.1700

Data Index: 2035371 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6824. Min Act: -0.1700

Data Index: 616597 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1800547 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6384. Min Act: -0.1700

Data Index: 6240405 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6706. Min Act: -0.1700

Data Index: 8472504 (Open Web Text)

Max Activating Token Index: 558

Text #6

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6258. Min Act: -0.1700

Data Index: 3372019 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6369. Min Act: -0.1700

Data Index: 2287912 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6340. Min Act: -0.1700

Data Index: 3699959 (Open Web Text)

Max Activating Token Index: 867

Text #9

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1928209 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6095. Min Act: -0.1700

Data Index: 2175137 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6028. Min Act: -0.1700

Data Index: 7369732 (Open Web Text)

Max Activating Token Index: 589

Text #12

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5897. Min Act: -0.1700

Data Index: 3306625 (Open Web Text)

Max Activating Token Index: 861

Text #13

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6085. Min Act: -0.1700

Data Index: 1449364 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6026. Min Act: -0.1700

Data Index: 6862298 (Open Web Text)

Max Activating Token Index: 812

Text #15

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5822. Min Act: -0.1700

Data Index: 4220027 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5980. Min Act: -0.1700

Data Index: 2146584 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5852. Min Act: -0.1700

Data Index: 2341753 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5897. Min Act: -0.1700

Data Index: 6875546 (Open Web Text)

Max Activating Token Index: 698

Text #19

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5896. Min Act: -0.1700

Data Index: 4301351 (Open Web Text)

Max Activating Token Index: 833