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

Dataset: Open Web Text

Neuron 2546 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: 3.7694. Min Range: -3.7694

Max Act: 3.7694. Min Act: -0.1700

Data Index: 5683962 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.7578. Min Act: -0.1700

Data Index: 8085316 (Open Web Text)

Max Activating Token Index: 565

Text #2

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.7301. Min Act: -0.1700

Data Index: 652456 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.7091. Min Act: -0.1700

Data Index: 6123329 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6948. Min Act: -0.1700

Data Index: 4401563 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.7093. Min Act: -0.1700

Data Index: 3112572 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6845. Min Act: -0.1700

Data Index: 3921867 (Open Web Text)

Max Activating Token Index: 450

Text #7

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6481. Min Act: -0.1700

Data Index: 544198 (Open Web Text)

Max Activating Token Index: 508

Text #8

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6454. Min Act: -0.1700

Data Index: 7010570 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5658. Min Act: -0.1700

Data Index: 4008171 (Open Web Text)

Max Activating Token Index: 178

Text #10

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6623. Min Act: -0.1700

Data Index: 5447182 (Open Web Text)

Max Activating Token Index: 453

Text #11

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6240. Min Act: -0.1700

Data Index: 752352 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6104. Min Act: -0.1700

Data Index: 3139958 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6040. Min Act: -0.1700

Data Index: 7975742 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6232. Min Act: -0.1700

Data Index: 5944711 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6041. Min Act: -0.1700

Data Index: 3787430 (Open Web Text)

Max Activating Token Index: 684

Text #16

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6216. Min Act: -0.1700

Data Index: 1616735 (Open Web Text)

Max Activating Token Index: 932

Text #17

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5999. Min Act: -0.1700

Data Index: 3815629 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5990. Min Act: -0.1700

Data Index: 6411882 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6117. Min Act: -0.1700

Data Index: 7210483 (Open Web Text)

Max Activating Token Index: 214