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

Dataset: Open Web Text

Neuron 145 in Layer 6

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: 3.3570. Min Range: -3.3570

Max Act: 3.3570. Min Act: -0.1700

Data Index: 4602474 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.1506. Min Act: -0.1700

Data Index: 7387728 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.1281. Min Act: -0.1700

Data Index: 7387729 (Open Web Text)

Max Activating Token Index: 385

Text #3

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0842. Min Act: -0.1700

Data Index: 6009365 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0950. Min Act: -0.1700

Data Index: 2532082 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0682. Min Act: -0.1700

Data Index: 7267238 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0418. Min Act: -0.1700

Data Index: 4784407 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1256786 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9699. Min Act: -0.1700

Data Index: 704445 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9679. Min Act: -0.1700

Data Index: 2723272 (Open Web Text)

Max Activating Token Index: 159

Text #10

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9809. Min Act: -0.1700

Data Index: 5548220 (Open Web Text)

Max Activating Token Index: 808

Text #11

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9687. Min Act: -0.1700

Data Index: 8728126 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9497. Min Act: -0.1700

Data Index: 2413531 (Open Web Text)

Max Activating Token Index: 339

Text #13

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9418. Min Act: -0.1700

Data Index: 7907225 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9502. Min Act: -0.1700

Data Index: 441706 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9524. Min Act: -0.1700

Data Index: 2217265 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9646. Min Act: -0.1700

Data Index: 1371202 (Open Web Text)

Max Activating Token Index: 747

Text #17

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9623. Min Act: -0.1700

Data Index: 3678119 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9450. Min Act: -0.1700

Data Index: 1084340 (Open Web Text)

Max Activating Token Index: 40

Text #19

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.9382. Min Act: -0.1700

Data Index: 2166694 (Open Web Text)

Max Activating Token Index: 18