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

Dataset: Open Web Text

Neuron 246 in Layer 2

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: 5.0462. Min Range: -5.0462

Max Act: 5.0462. Min Act: -0.1700

Data Index: 2609444 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 5.0462. Min Range: -5.0462

Max Act: 5.0307. Min Act: -0.1700

Data Index: 1701362 (Open Web Text)

Max Activating Token Index: 169

Text #2

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.9835. Min Act: -0.1700

Data Index: 8528321 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.7999. Min Act: -0.1700

Data Index: 7611340 (Open Web Text)

Max Activating Token Index: 920

Text #4

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.7919. Min Act: -0.1700

Data Index: 5572809 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6979. Min Act: -0.1700

Data Index: 973456 (Open Web Text)

Max Activating Token Index: 982

Text #6

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.7167. Min Act: -0.1700

Data Index: 8104637 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6892. Min Act: -0.1700

Data Index: 6922171 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6683. Min Act: -0.1700

Data Index: 336080 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6780. Min Act: -0.1700

Data Index: 2677224 (Open Web Text)

Max Activating Token Index: 685

Text #10

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6729. Min Act: -0.1700

Data Index: 4307224 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6686. Min Act: -0.1700

Data Index: 4077145 (Open Web Text)

Max Activating Token Index: 914

Text #12

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6523. Min Act: -0.1700

Data Index: 4451645 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6156. Min Act: -0.1700

Data Index: 5047495 (Open Web Text)

Max Activating Token Index: 970

Text #14

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6482. Min Act: -0.1700

Data Index: 6956896 (Open Web Text)

Max Activating Token Index: 667

Text #15

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.5734. Min Act: -0.1700

Data Index: 314779 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.5944. Min Act: -0.1700

Data Index: 212165 (Open Web Text)

Max Activating Token Index: 86

Text #17

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.6395. Min Act: -0.1700

Data Index: 7142078 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.5508. Min Act: -0.1700

Data Index: 7007104 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 5.0462. Min Range: -5.0462

Max Act: 4.5938. Min Act: -0.1700

Data Index: 4897498 (Open Web Text)

Max Activating Token Index: 600