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

Dataset: Open Web Text

Neuron 330 in Layer 2

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: 2.3902. Min Range: -2.3902

Max Act: 2.3902. Min Act: -0.1700

Data Index: 1991861 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.3525. Min Act: -0.1700

Data Index: 679463 (Open Web Text)

Max Activating Token Index: 637

Text #2

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.3388. Min Act: -0.1700

Data Index: 1705935 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2982. Min Act: -0.1700

Data Index: 1376253 (Open Web Text)

Max Activating Token Index: 190

Text #4

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2780. Min Act: -0.1700

Data Index: 5644269 (Open Web Text)

Max Activating Token Index: 87

Text #5

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2931. Min Act: -0.1700

Data Index: 1748540 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2916. Min Act: -0.1700

Data Index: 290843 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2949. Min Act: -0.1700

Data Index: 7180088 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2755. Min Act: -0.1700

Data Index: 4718280 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2502. Min Act: -0.1700

Data Index: 749996 (Open Web Text)

Max Activating Token Index: 1018

Text #10

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2536. Min Act: -0.1700

Data Index: 733438 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2898. Min Act: -0.1700

Data Index: 6551189 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2745. Min Act: -0.1700

Data Index: 6372656 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2778. Min Act: -0.1700

Data Index: 5882861 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2413. Min Act: -0.1700

Data Index: 5756384 (Open Web Text)

Max Activating Token Index: 942

Text #15

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2654. Min Act: -0.1700

Data Index: 3037387 (Open Web Text)

Max Activating Token Index: 883

Text #16

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2618. Min Act: -0.1700

Data Index: 640982 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2645. Min Act: -0.1700

Data Index: 628339 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2632. Min Act: -0.1700

Data Index: 2520223 (Open Web Text)

Max Activating Token Index: 204

Text #19

Max Range: 2.3902. Min Range: -2.3902

Max Act: 2.2578. Min Act: -0.1700

Data Index: 8066828 (Open Web Text)

Max Activating Token Index: 149