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

Dataset: Open Web Text

Neuron 619 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: 3.2250. Min Range: -3.2250

Max Act: 3.2057. Min Act: -0.1700

Data Index: 77901 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.2250. Min Act: -0.1700

Data Index: 2756150 (Open Web Text)

Max Activating Token Index: 848

Text #2

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.1282. Min Act: -0.1700

Data Index: 33262 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.1077. Min Act: -0.1700

Data Index: 8097644 (Open Web Text)

Max Activating Token Index: 699

Text #4

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0771. Min Act: -0.1700

Data Index: 2930229 (Open Web Text)

Max Activating Token Index: 378

Text #5

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0576. Min Act: -0.1700

Data Index: 4468070 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0637. Min Act: -0.1700

Data Index: 1395816 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0516. Min Act: -0.1700

Data Index: 6403950 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0315. Min Act: -0.1700

Data Index: 1034749 (Open Web Text)

Max Activating Token Index: 394

Text #9

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0709. Min Act: -0.1700

Data Index: 8471412 (Open Web Text)

Max Activating Token Index: 180

Text #10

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0443. Min Act: -0.1700

Data Index: 4077175 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0393. Min Act: -0.1700

Data Index: 2638931 (Open Web Text)

Max Activating Token Index: 604

Text #12

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0651. Min Act: -0.1700

Data Index: 4355697 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0528. Min Act: -0.1700

Data Index: 194967 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0015. Min Act: -0.1700

Data Index: 7768191 (Open Web Text)

Max Activating Token Index: 687

Text #15

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0234. Min Act: -0.1700

Data Index: 2135004 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0265. Min Act: -0.1700

Data Index: 5671192 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0020. Min Act: -0.1700

Data Index: 2628074 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0075. Min Act: -0.1700

Data Index: 1433808 (Open Web Text)

Max Activating Token Index: 770

Text #19

Max Range: 3.2250. Min Range: -3.2250

Max Act: 3.0213. Min Act: -0.1700

Data Index: 1143173 (Open Web Text)

Max Activating Token Index: 811