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

Dataset: Open Web Text

Neuron 736 in Layer 5

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: 4.7907. Min Range: -4.7907

Max Act: 4.7907. Min Act: -0.1700

Data Index: 1200650 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.5180. Min Act: -0.1700

Data Index: 5312663 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.5258. Min Act: -0.1700

Data Index: 3290409 (Open Web Text)

Max Activating Token Index: 227

Text #3

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.5654. Min Act: -0.1700

Data Index: 7734032 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.5194. Min Act: -0.1700

Data Index: 6858022 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4770. Min Act: -0.1700

Data Index: 4595204 (Open Web Text)

Max Activating Token Index: 533

Text #6

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4465. Min Act: -0.1700

Data Index: 2606730 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4448. Min Act: -0.1700

Data Index: 2565388 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4451. Min Act: -0.1700

Data Index: 7185684 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4351. Min Act: -0.1700

Data Index: 8311157 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4303. Min Act: -0.1700

Data Index: 4068173 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4094. Min Act: -0.1700

Data Index: 7040997 (Open Web Text)

Max Activating Token Index: 790

Text #12

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.3912. Min Act: -0.1700

Data Index: 6401419 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.3992. Min Act: -0.1700

Data Index: 4171889 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4163. Min Act: -0.1700

Data Index: 2331931 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.3608. Min Act: -0.1700

Data Index: 245867 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.4005. Min Act: -0.1700

Data Index: 8396185 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.3428. Min Act: -0.1700

Data Index: 3513040 (Open Web Text)

Max Activating Token Index: 385

Text #18

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.3900. Min Act: -0.1700

Data Index: 7881032 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.7907. Min Range: -4.7907

Max Act: 4.3481. Min Act: -0.1700

Data Index: 1110409 (Open Web Text)

Max Activating Token Index: 329