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

Dataset: Open Web Text

Neuron 2550 in Layer 4

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: 3.0734. Min Range: -3.0734

Max Act: 3.0734. Min Act: -0.1700

Data Index: 2857216 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 3.0734. Min Range: -3.0734

Max Act: 3.0432. Min Act: -0.1700

Data Index: 7356426 (Open Web Text)

Max Activating Token Index: 737

Text #2

Max Range: 3.0734. Min Range: -3.0734

Max Act: 3.0048. Min Act: -0.1700

Data Index: 2570657 (Open Web Text)

Max Activating Token Index: 227

Text #3

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.9101. Min Act: -0.1700

Data Index: 3569158 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.9115. Min Act: -0.1700

Data Index: 6163640 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8648. Min Act: -0.1700

Data Index: 1373799 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8541. Min Act: -0.1700

Data Index: 6077127 (Open Web Text)

Max Activating Token Index: 546

Text #7

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8466. Min Act: -0.1700

Data Index: 8417849 (Open Web Text)

Max Activating Token Index: 132

Text #8

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8244. Min Act: -0.1700

Data Index: 2221874 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8419. Min Act: -0.1700

Data Index: 7236269 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8332. Min Act: -0.1700

Data Index: 2898242 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.7983. Min Act: -0.1700

Data Index: 6835083 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8174. Min Act: -0.1700

Data Index: 289123 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8202. Min Act: -0.1700

Data Index: 3541978 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8108. Min Act: -0.1700

Data Index: 5573722 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8296. Min Act: -0.1700

Data Index: 2252266 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8132. Min Act: -0.1700

Data Index: 581651 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8135. Min Act: -0.1700

Data Index: 5261204 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.7935. Min Act: -0.1700

Data Index: 999806 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 3.0734. Min Range: -3.0734

Max Act: 2.8034. Min Act: -0.1700

Data Index: 6720868 (Open Web Text)

Max Activating Token Index: 721