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

Dataset: Open Web Text

Neuron 2536 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: 3.4026. Min Range: -3.4026

Max Act: 3.4026. Min Act: -0.1700

Data Index: 3997262 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.3022. Min Act: -0.1700

Data Index: 2786330 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2669. Min Act: -0.1700

Data Index: 3349033 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2390. Min Act: -0.1700

Data Index: 5617347 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2375. Min Act: -0.1700

Data Index: 7822304 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2286. Min Act: -0.1700

Data Index: 3961253 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2226. Min Act: -0.1700

Data Index: 8408474 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2298. Min Act: -0.1700

Data Index: 4768067 (Open Web Text)

Max Activating Token Index: 435

Text #8

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2388. Min Act: -0.1700

Data Index: 2394123 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2073. Min Act: -0.1700

Data Index: 5101737 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1865. Min Act: -0.1700

Data Index: 1769733 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2020. Min Act: -0.1700

Data Index: 2811574 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.2242. Min Act: -0.1700

Data Index: 508222 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1677. Min Act: -0.1700

Data Index: 227828 (Open Web Text)

Max Activating Token Index: 918

Text #14

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1188569 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1733. Min Act: -0.1700

Data Index: 7607980 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1728. Min Act: -0.1700

Data Index: 2849694 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1830. Min Act: -0.1700

Data Index: 4948703 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1820. Min Act: -0.1700

Data Index: 6070331 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 3.4026. Min Range: -3.4026

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1562649 (Open Web Text)

Max Activating Token Index: 724