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

Dataset: Open Web Text

Neuron 711 in Layer 1

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: 1.7424. Min Range: -1.7424

Max Act: 1.7424. Min Act: -0.1700

Data Index: 6348013 (Open Web Text)

Max Activating Token Index: 361

Text #1

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7383. Min Act: -0.1699

Data Index: 283679 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7219. Min Act: -0.1696

Data Index: 1400639 (Open Web Text)

Max Activating Token Index: 887

Text #3

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7045. Min Act: -0.1700

Data Index: 4360550 (Open Web Text)

Max Activating Token Index: 116

Text #4

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6961. Min Act: -0.1700

Data Index: 737475 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7035. Min Act: -0.1700

Data Index: 4160325 (Open Web Text)

Max Activating Token Index: 918

Text #6

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6953. Min Act: -0.1700

Data Index: 5599031 (Open Web Text)

Max Activating Token Index: 157

Text #7

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6945. Min Act: -0.1700

Data Index: 5820775 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6909. Min Act: -0.1700

Data Index: 5340899 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6797. Min Act: -0.1700

Data Index: 3797109 (Open Web Text)

Max Activating Token Index: 334

Text #10

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6823. Min Act: -0.1700

Data Index: 2984160 (Open Web Text)

Max Activating Token Index: 452

Text #11

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6725. Min Act: -0.1700

Data Index: 2020059 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6731. Min Act: -0.1699

Data Index: 5191989 (Open Web Text)

Max Activating Token Index: 213

Text #13

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6730. Min Act: -0.1700

Data Index: 5740901 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6785. Min Act: -0.1699

Data Index: 5796291 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6645. Min Act: -0.1700

Data Index: 6265521 (Open Web Text)

Max Activating Token Index: 230

Text #16

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6685. Min Act: -0.1700

Data Index: 6634753 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6569. Min Act: -0.1700

Data Index: 7873881 (Open Web Text)

Max Activating Token Index: 902

Text #18

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6619. Min Act: -0.1700

Data Index: 7963278 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6685. Min Act: -0.1700

Data Index: 97488 (Open Web Text)

Max Activating Token Index: 215