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

Dataset: Open Web Text

Neuron 2848 in Layer 1

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: 3.6831. Min Range: -3.6831

Max Act: 3.6831. Min Act: -0.1700

Data Index: 2197454 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5970. Min Act: -0.1700

Data Index: 5894032 (Open Web Text)

Max Activating Token Index: 335

Text #2

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5445. Min Act: -0.1700

Data Index: 3874638 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5512. Min Act: -0.1700

Data Index: 3337434 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5250. Min Act: -0.1700

Data Index: 6722280 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5104. Min Act: -0.1700

Data Index: 4956039 (Open Web Text)

Max Activating Token Index: 87

Text #6

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5106. Min Act: -0.1700

Data Index: 6174628 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5003. Min Act: -0.1700

Data Index: 2624503 (Open Web Text)

Max Activating Token Index: 124

Text #8

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4924. Min Act: -0.1700

Data Index: 2801250 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5052. Min Act: -0.1700

Data Index: 6410991 (Open Web Text)

Max Activating Token Index: 505

Text #10

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4796. Min Act: -0.1700

Data Index: 6533243 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4854. Min Act: -0.1700

Data Index: 2003250 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4832. Min Act: -0.1700

Data Index: 7735519 (Open Web Text)

Max Activating Token Index: 619

Text #13

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4885. Min Act: -0.1700

Data Index: 171569 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4847. Min Act: -0.1700

Data Index: 970220 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4843. Min Act: -0.1700

Data Index: 4871640 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4735. Min Act: -0.1700

Data Index: 79498 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4650. Min Act: -0.1700

Data Index: 6239498 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4721. Min Act: -0.1700

Data Index: 466047 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.4654. Min Act: -0.1700

Data Index: 537546 (Open Web Text)

Max Activating Token Index: 509