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

Dataset: Open Web Text

Neuron 2565 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: 5.3817. Min Range: -5.3817

Max Act: 5.3817. Min Act: -0.1700

Data Index: 351786 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.3564. Min Act: -0.1700

Data Index: 6564487 (Open Web Text)

Max Activating Token Index: 617

Text #2

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.2798. Min Act: -0.1700

Data Index: 4535952 (Open Web Text)

Max Activating Token Index: 768

Text #3

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.2759. Min Act: -0.1700

Data Index: 5910240 (Open Web Text)

Max Activating Token Index: 195

Text #4

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.3091. Min Act: -0.1700

Data Index: 2810652 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.3073. Min Act: -0.1700

Data Index: 2043987 (Open Web Text)

Max Activating Token Index: 639

Text #6

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1978. Min Act: -0.1700

Data Index: 8254605 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.2107. Min Act: -0.1700

Data Index: 703625 (Open Web Text)

Max Activating Token Index: 512

Text #8

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1815. Min Act: -0.1700

Data Index: 3164414 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1819. Min Act: -0.1700

Data Index: 7170680 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1569. Min Act: -0.1700

Data Index: 3341973 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1802. Min Act: -0.1700

Data Index: 2343221 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1726. Min Act: -0.1700

Data Index: 3666997 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1334. Min Act: -0.1700

Data Index: 3055713 (Open Web Text)

Max Activating Token Index: 708

Text #14

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1477. Min Act: -0.1700

Data Index: 6348393 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1031. Min Act: -0.1700

Data Index: 6422477 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1576. Min Act: -0.1700

Data Index: 4196526 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1523. Min Act: -0.1700

Data Index: 3584355 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1297. Min Act: -0.1700

Data Index: 792197 (Open Web Text)

Max Activating Token Index: 451

Text #19

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.1413. Min Act: -0.1700

Data Index: 1270606 (Open Web Text)

Max Activating Token Index: 319