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

Dataset: Open Web Text

Neuron 661 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: 3.0282. Min Range: -3.0282

Max Act: 3.0282. Min Act: -0.1700

Data Index: 5459721 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9886. Min Act: -0.1700

Data Index: 5733538 (Open Web Text)

Max Activating Token Index: 719

Text #2

Max Range: 3.0282. Min Range: -3.0282

Max Act: 3.0138. Min Act: -0.1700

Data Index: 6570173 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9605. Min Act: -0.1700

Data Index: 4891742 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9534. Min Act: -0.1700

Data Index: 6906084 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9668. Min Act: -0.1700

Data Index: 8555775 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9681. Min Act: -0.1700

Data Index: 2607401 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9570. Min Act: -0.1700

Data Index: 1747916 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9443. Min Act: -0.1700

Data Index: 6382460 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9526. Min Act: -0.1700

Data Index: 8718722 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9354. Min Act: -0.1700

Data Index: 5683436 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9330. Min Act: -0.1700

Data Index: 3481749 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9289. Min Act: -0.1700

Data Index: 4573907 (Open Web Text)

Max Activating Token Index: 516

Text #13

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9370. Min Act: -0.1700

Data Index: 2033180 (Open Web Text)

Max Activating Token Index: 743

Text #14

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9755. Min Act: -0.1700

Data Index: 2565843 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9035. Min Act: -0.1700

Data Index: 7110670 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9279. Min Act: -0.1700

Data Index: 2754481 (Open Web Text)

Max Activating Token Index: 883

Text #17

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9190. Min Act: -0.1700

Data Index: 5408925 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.9384. Min Act: -0.1700

Data Index: 6506553 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.8977. Min Act: -0.1700

Data Index: 6229433 (Open Web Text)

Max Activating Token Index: 182