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

Dataset: Open Web Text

Neuron 2301 in Layer 0

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: 3.3481. Min Range: -3.3481

Max Act: 3.3481. Min Act: -0.1700

Data Index: 5074295 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 3.3481. Min Range: -3.3481

Max Act: 3.0974. Min Act: -0.1700

Data Index: 1119208 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 3.3481. Min Range: -3.3481

Max Act: 3.0731. Min Act: -0.1700

Data Index: 5074303 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 3.3481. Min Range: -3.3481

Max Act: 3.0200. Min Act: -0.1700

Data Index: 3160990 (Open Web Text)

Max Activating Token Index: 729

Text #4

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.9721. Min Act: -0.1700

Data Index: 6299059 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.9375. Min Act: -0.1700

Data Index: 5209658 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.9271. Min Act: -0.1700

Data Index: 6228102 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8875. Min Act: -0.1700

Data Index: 7558677 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8823. Min Act: -0.1700

Data Index: 5209661 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8700. Min Act: -0.1700

Data Index: 7825203 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8794. Min Act: -0.1700

Data Index: 7825185 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8718. Min Act: -0.1700

Data Index: 5209659 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8598. Min Act: -0.1700

Data Index: 4483446 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1811466 (Open Web Text)

Max Activating Token Index: 849

Text #14

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8552. Min Act: -0.1700

Data Index: 2963855 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8545. Min Act: -0.1700

Data Index: 5074300 (Open Web Text)

Max Activating Token Index: 862

Text #16

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8418. Min Act: -0.1700

Data Index: 1857622 (Open Web Text)

Max Activating Token Index: 346

Text #17

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8442. Min Act: -0.1700

Data Index: 5209657 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8316. Min Act: -0.1700

Data Index: 5975136 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 3.3481. Min Range: -3.3481

Max Act: 2.8233. Min Act: -0.1700

Data Index: 5209660 (Open Web Text)

Max Activating Token Index: 989