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

Dataset: Open Web Text

Neuron 2890 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: 5.1854. Min Range: -5.1854

Max Act: 5.1854. Min Act: -0.1700

Data Index: 7293121 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 5.1854. Min Range: -5.1854

Max Act: 5.0697. Min Act: -0.1700

Data Index: 3129548 (Open Web Text)

Max Activating Token Index: 220

Text #2

Max Range: 5.1854. Min Range: -5.1854

Max Act: 5.0772. Min Act: -0.1700

Data Index: 1399632 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.9429. Min Act: -0.1700

Data Index: 4944625 (Open Web Text)

Max Activating Token Index: 324

Text #4

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.8948. Min Act: -0.1700

Data Index: 2700752 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.8513. Min Act: -0.1700

Data Index: 1134853 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.8698. Min Act: -0.1700

Data Index: 3006665 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.8234. Min Act: -0.1700

Data Index: 5642319 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.8027. Min Act: -0.1700

Data Index: 4536257 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7570. Min Act: -0.1700

Data Index: 2886781 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7869. Min Act: -0.1700

Data Index: 6715722 (Open Web Text)

Max Activating Token Index: 896

Text #11

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7183. Min Act: -0.1700

Data Index: 769160 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7264. Min Act: -0.1700

Data Index: 7545326 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7191. Min Act: -0.1700

Data Index: 7065304 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7232. Min Act: -0.1700

Data Index: 1415645 (Open Web Text)

Max Activating Token Index: 851

Text #15

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.6793. Min Act: -0.1700

Data Index: 7831751 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7153. Min Act: -0.1700

Data Index: 5516355 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.7078. Min Act: -0.1700

Data Index: 8319451 (Open Web Text)

Max Activating Token Index: 624

Text #18

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.6454. Min Act: -0.1700

Data Index: 4360569 (Open Web Text)

Max Activating Token Index: 63

Text #19

Max Range: 5.1854. Min Range: -5.1854

Max Act: 4.6760. Min Act: -0.1700

Data Index: 7984682 (Open Web Text)

Max Activating Token Index: 826