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

Dataset: Open Web Text

Neuron 748 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: 4.4251. Min Range: -4.4251

Max Act: 4.4251. Min Act: -0.1700

Data Index: 7066959 (Open Web Text)

Max Activating Token Index: 822

Text #1

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.4091. Min Act: -0.1700

Data Index: 3619940 (Open Web Text)

Max Activating Token Index: 237

Text #2

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3659. Min Act: -0.1700

Data Index: 7939331 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3554. Min Act: -0.1700

Data Index: 5863718 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3032. Min Act: -0.1700

Data Index: 4843597 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3333. Min Act: -0.1700

Data Index: 6657372 (Open Web Text)

Max Activating Token Index: 68

Text #6

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2934. Min Act: -0.1700

Data Index: 2235846 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2949. Min Act: -0.1700

Data Index: 2264378 (Open Web Text)

Max Activating Token Index: 823

Text #8

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3069. Min Act: -0.1700

Data Index: 844591 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2827. Min Act: -0.1700

Data Index: 5030110 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2711. Min Act: -0.1700

Data Index: 8052309 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2778. Min Act: -0.1700

Data Index: 7460869 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2755. Min Act: -0.1700

Data Index: 7145939 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2473. Min Act: -0.1700

Data Index: 528903 (Open Web Text)

Max Activating Token Index: 223

Text #14

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2656. Min Act: -0.1700

Data Index: 3181357 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2895. Min Act: -0.1700

Data Index: 1812406 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2916. Min Act: -0.1700

Data Index: 4576378 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.3098. Min Act: -0.1700

Data Index: 1775582 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2326. Min Act: -0.1700

Data Index: 4976768 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 4.4251. Min Range: -4.4251

Max Act: 4.2356. Min Act: -0.1700

Data Index: 2957412 (Open Web Text)

Max Activating Token Index: 718