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

Dataset: Open Web Text

Neuron 2791 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: 3.2123. Min Range: -3.2123

Max Act: 3.2123. Min Act: -0.1700

Data Index: 6907733 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.1510. Min Act: -0.1700

Data Index: 3595355 (Open Web Text)

Max Activating Token Index: 296

Text #2

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0992. Min Act: -0.1700

Data Index: 2481049 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0649. Min Act: -0.1700

Data Index: 6871439 (Open Web Text)

Max Activating Token Index: 338

Text #4

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0618. Min Act: -0.1700

Data Index: 738436 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0408. Min Act: -0.1700

Data Index: 7875994 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0272. Min Act: -0.1700

Data Index: 6664304 (Open Web Text)

Max Activating Token Index: 513

Text #7

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0417. Min Act: -0.1700

Data Index: 7003487 (Open Web Text)

Max Activating Token Index: 129

Text #8

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0272. Min Act: -0.1700

Data Index: 15007 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0091. Min Act: -0.1700

Data Index: 6850119 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 3.2123. Min Range: -3.2123

Max Act: 2.9938. Min Act: -0.1700

Data Index: 1069061 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0215. Min Act: -0.1700

Data Index: 7620501 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0315. Min Act: -0.1700

Data Index: 1213799 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 3.2123. Min Range: -3.2123

Max Act: 2.9998. Min Act: -0.1700

Data Index: 1261911 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0086. Min Act: -0.1700

Data Index: 5084931 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 3.2123. Min Range: -3.2123

Max Act: 3.0109. Min Act: -0.1700

Data Index: 8051376 (Open Web Text)

Max Activating Token Index: 952

Text #16

Max Range: 3.2123. Min Range: -3.2123

Max Act: 2.9967. Min Act: -0.1700

Data Index: 2648914 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 3.2123. Min Range: -3.2123

Max Act: 2.9778. Min Act: -0.1700

Data Index: 6349663 (Open Web Text)

Max Activating Token Index: 916

Text #18

Max Range: 3.2123. Min Range: -3.2123

Max Act: 2.9890. Min Act: -0.1700

Data Index: 5600349 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 3.2123. Min Range: -3.2123

Max Act: 2.9750. Min Act: -0.1700

Data Index: 5844674 (Open Web Text)

Max Activating Token Index: 542