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

Dataset: Open Web Text

Neuron 2135 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: 4.3513. Min Range: -4.3513

Max Act: 4.2885. Min Act: -0.1700

Data Index: 7115792 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2979. Min Act: -0.1700

Data Index: 6373126 (Open Web Text)

Max Activating Token Index: 283

Text #2

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3513. Min Act: -0.1700

Data Index: 6165755 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3406. Min Act: -0.1700

Data Index: 3440167 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3313. Min Act: -0.1700

Data Index: 3372578 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3349. Min Act: -0.1700

Data Index: 261343 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3053. Min Act: -0.1700

Data Index: 7313070 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3233. Min Act: -0.1700

Data Index: 1605285 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3058. Min Act: -0.1700

Data Index: 1164041 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2638. Min Act: -0.1700

Data Index: 5758447 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2819. Min Act: -0.1700

Data Index: 8287625 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3055. Min Act: -0.1700

Data Index: 7929290 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3247. Min Act: -0.1700

Data Index: 5387457 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2561. Min Act: -0.1700

Data Index: 3187626 (Open Web Text)

Max Activating Token Index: 898

Text #14

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2541. Min Act: -0.1700

Data Index: 2701409 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.3085. Min Act: -0.1700

Data Index: 5430946 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2610. Min Act: -0.1700

Data Index: 6227259 (Open Web Text)

Max Activating Token Index: 885

Text #17

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2890. Min Act: -0.1700

Data Index: 6255808 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2611. Min Act: -0.1700

Data Index: 6456013 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 4.3513. Min Range: -4.3513

Max Act: 4.2875. Min Act: -0.1700

Data Index: 5312270 (Open Web Text)

Max Activating Token Index: 828