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

Dataset: Open Web Text

Neuron 312 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: 4.2485. Min Range: -4.2485

Max Act: 4.2485. Min Act: -0.1700

Data Index: 3939411 (Open Web Text)

Max Activating Token Index: 210

Text #1

Max Range: 4.2485. Min Range: -4.2485

Max Act: 4.0618. Min Act: -0.1700

Data Index: 2013076 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 4.2485. Min Range: -4.2485

Max Act: 4.0225. Min Act: -0.1700

Data Index: 5712169 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.9673. Min Act: -0.1700

Data Index: 4119639 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.9482. Min Act: -0.1700

Data Index: 831126 (Open Web Text)

Max Activating Token Index: 329

Text #5

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.9094. Min Act: -0.1700

Data Index: 7486104 (Open Web Text)

Max Activating Token Index: 702

Text #6

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.9198. Min Act: -0.1700

Data Index: 5421954 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8603. Min Act: -0.1700

Data Index: 756111 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.9064. Min Act: -0.1700

Data Index: 5894678 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.9061. Min Act: -0.1700

Data Index: 8668073 (Open Web Text)

Max Activating Token Index: 336

Text #10

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8719. Min Act: -0.1700

Data Index: 4952759 (Open Web Text)

Max Activating Token Index: 868

Text #11

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8628. Min Act: -0.1700

Data Index: 421839 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8799. Min Act: -0.1700

Data Index: 5013927 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8620. Min Act: -0.1700

Data Index: 2848466 (Open Web Text)

Max Activating Token Index: 529

Text #14

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8333. Min Act: -0.1700

Data Index: 1529699 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8078. Min Act: -0.1700

Data Index: 1225807 (Open Web Text)

Max Activating Token Index: 1019

Text #16

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8567. Min Act: -0.1700

Data Index: 3597175 (Open Web Text)

Max Activating Token Index: 762

Text #17

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.7825. Min Act: -0.1700

Data Index: 3000834 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.7793. Min Act: -0.1700

Data Index: 1085037 (Open Web Text)

Max Activating Token Index: 963

Text #19

Max Range: 4.2485. Min Range: -4.2485

Max Act: 3.8278. Min Act: -0.1700

Data Index: 3444052 (Open Web Text)

Max Activating Token Index: 502