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

Dataset: Open Web Text

Neuron 1065 in Layer 1

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: 1.7538. Min Range: -1.7538

Max Act: 1.7538. Min Act: -0.1700

Data Index: 6442217 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7205. Min Act: -0.1700

Data Index: 7881362 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7256. Min Act: -0.1700

Data Index: 2360554 (Open Web Text)

Max Activating Token Index: 518

Text #3

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7157. Min Act: -0.1697

Data Index: 2950345 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7148. Min Act: -0.1700

Data Index: 3705058 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7059. Min Act: -0.1700

Data Index: 3242190 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6959. Min Act: -0.1700

Data Index: 5776809 (Open Web Text)

Max Activating Token Index: 692

Text #7

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6926. Min Act: -0.1700

Data Index: 4607586 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7000. Min Act: -0.1700

Data Index: 713170 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6791. Min Act: -0.1699

Data Index: 8315118 (Open Web Text)

Max Activating Token Index: 53

Text #10

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6799. Min Act: -0.1700

Data Index: 5663134 (Open Web Text)

Max Activating Token Index: 260

Text #11

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6740. Min Act: -0.1700

Data Index: 1462119 (Open Web Text)

Max Activating Token Index: 618

Text #12

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6740. Min Act: -0.1700

Data Index: 1915685 (Open Web Text)

Max Activating Token Index: 886

Text #13

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6686. Min Act: -0.1700

Data Index: 862626 (Open Web Text)

Max Activating Token Index: 123

Text #14

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6701. Min Act: -0.1700

Data Index: 8273567 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6643. Min Act: -0.1700

Data Index: 5771886 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6663. Min Act: -0.1700

Data Index: 1503107 (Open Web Text)

Max Activating Token Index: 253

Text #17

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6560. Min Act: -0.1700

Data Index: 7862008 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6485. Min Act: -0.1700

Data Index: 4777902 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6566. Min Act: -0.1695

Data Index: 2220525 (Open Web Text)

Max Activating Token Index: 193