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

Dataset: Open Web Text

Neuron 1893 in Layer 3

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: 4.8335. Min Range: -4.8335

Max Act: 4.8335. Min Act: -0.1700

Data Index: 3609482 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7700. Min Act: -0.1700

Data Index: 5811172 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.8166. Min Act: -0.1700

Data Index: 6332977 (Open Web Text)

Max Activating Token Index: 264

Text #3

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7933. Min Act: -0.1700

Data Index: 6049468 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7378. Min Act: -0.1700

Data Index: 2858421 (Open Web Text)

Max Activating Token Index: 248

Text #5

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7241. Min Act: -0.1700

Data Index: 6760633 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7316. Min Act: -0.1700

Data Index: 4948489 (Open Web Text)

Max Activating Token Index: 182

Text #7

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7819. Min Act: -0.1700

Data Index: 3970204 (Open Web Text)

Max Activating Token Index: 803

Text #8

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7626. Min Act: -0.1700

Data Index: 6669002 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7082. Min Act: -0.1700

Data Index: 485754 (Open Web Text)

Max Activating Token Index: 746

Text #10

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6906. Min Act: -0.1700

Data Index: 7071828 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.7328. Min Act: -0.1700

Data Index: 2508921 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6486. Min Act: -0.1700

Data Index: 1798083 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6989. Min Act: -0.1700

Data Index: 5948088 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6477. Min Act: -0.1700

Data Index: 69369 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6523. Min Act: -0.1700

Data Index: 5998865 (Open Web Text)

Max Activating Token Index: 842

Text #16

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6668. Min Act: -0.1700

Data Index: 729223 (Open Web Text)

Max Activating Token Index: 983

Text #17

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6287. Min Act: -0.1700

Data Index: 924408 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6647. Min Act: -0.1700

Data Index: 5536563 (Open Web Text)

Max Activating Token Index: 681

Text #19

Max Range: 4.8335. Min Range: -4.8335

Max Act: 4.6346. Min Act: -0.1700

Data Index: 6489362 (Open Web Text)

Max Activating Token Index: 403