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

Dataset: Open Web Text

Neuron 2544 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: 4.2366. Min Range: -4.2366

Max Act: 4.2366. Min Act: -0.1700

Data Index: 1699797 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.1237. Min Act: -0.1700

Data Index: 3668152 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0673. Min Act: -0.1700

Data Index: 3181156 (Open Web Text)

Max Activating Token Index: 549

Text #3

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0178. Min Act: -0.1700

Data Index: 6066737 (Open Web Text)

Max Activating Token Index: 846

Text #4

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.1027. Min Act: -0.1700

Data Index: 4007289 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0366. Min Act: -0.1700

Data Index: 4090040 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0056. Min Act: -0.1700

Data Index: 1663296 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.1020. Min Act: -0.1700

Data Index: 5981118 (Open Web Text)

Max Activating Token Index: 586

Text #8

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0484. Min Act: -0.1700

Data Index: 5536125 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0367. Min Act: -0.1700

Data Index: 415068 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0738. Min Act: -0.1700

Data Index: 7872063 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9942. Min Act: -0.1700

Data Index: 5018874 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 4.2366. Min Range: -4.2366

Max Act: 4.0132. Min Act: -0.1700

Data Index: 6509420 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9919. Min Act: -0.1700

Data Index: 8578174 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9724. Min Act: -0.1700

Data Index: 4557359 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9486. Min Act: -0.1700

Data Index: 4181004 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9645. Min Act: -0.1700

Data Index: 1976785 (Open Web Text)

Max Activating Token Index: 805

Text #17

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.8978. Min Act: -0.1700

Data Index: 132570 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9760. Min Act: -0.1700

Data Index: 495383 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.2366. Min Range: -4.2366

Max Act: 3.9165. Min Act: -0.1700

Data Index: 5509696 (Open Web Text)

Max Activating Token Index: 179