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

Dataset: Open Web Text

Neuron 2051 in Layer 4

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: 5.1940. Min Range: -5.1940

Max Act: 5.1940. Min Act: -0.1700

Data Index: 2006091 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1286. Min Act: -0.1700

Data Index: 4835247 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1421. Min Act: -0.1700

Data Index: 3894259 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0382. Min Act: -0.1700

Data Index: 6059725 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9760. Min Act: -0.1700

Data Index: 4314176 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8914. Min Act: -0.1700

Data Index: 3682212 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9561. Min Act: -0.1700

Data Index: 974076 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9728. Min Act: -0.1700

Data Index: 8548524 (Open Web Text)

Max Activating Token Index: 237

Text #8

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9194. Min Act: -0.1700

Data Index: 7983304 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9365. Min Act: -0.1700

Data Index: 7835278 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9263. Min Act: -0.1700

Data Index: 6107067 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9372. Min Act: -0.1700

Data Index: 117293 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9608. Min Act: -0.1700

Data Index: 5407374 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9447. Min Act: -0.1700

Data Index: 7789157 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9785. Min Act: -0.1700

Data Index: 7686189 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9600. Min Act: -0.1700

Data Index: 5056606 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8844. Min Act: -0.1700

Data Index: 454942 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9462. Min Act: -0.1700

Data Index: 1935152 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9088. Min Act: -0.1700

Data Index: 6889945 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8868. Min Act: -0.1700

Data Index: 3127263 (Open Web Text)

Max Activating Token Index: 304