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

Dataset: Open Web Text

Neuron 424 in Layer 4

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: 2.9206. Min Range: -2.9206

Max Act: 2.9206. Min Act: -0.1700

Data Index: 8648511 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8869. Min Act: -0.1700

Data Index: 6831272 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8568. Min Act: -0.1700

Data Index: 7459627 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8597. Min Act: -0.1700

Data Index: 8495793 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8480. Min Act: -0.1700

Data Index: 813280 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8182. Min Act: -0.1700

Data Index: 8178460 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8050. Min Act: -0.1700

Data Index: 8138981 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.8157. Min Act: -0.1700

Data Index: 1326007 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7801. Min Act: -0.1700

Data Index: 8662682 (Open Web Text)

Max Activating Token Index: 846

Text #9

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7818. Min Act: -0.1700

Data Index: 249500 (Open Web Text)

Max Activating Token Index: 823

Text #10

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7818. Min Act: -0.1700

Data Index: 6981554 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7742. Min Act: -0.1700

Data Index: 4581964 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7609. Min Act: -0.1700

Data Index: 5550372 (Open Web Text)

Max Activating Token Index: 537

Text #13

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7773. Min Act: -0.1700

Data Index: 3166593 (Open Web Text)

Max Activating Token Index: 975

Text #14

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7642. Min Act: -0.1700

Data Index: 3488204 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7657. Min Act: -0.1700

Data Index: 1808456 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7144. Min Act: -0.1700

Data Index: 713833 (Open Web Text)

Max Activating Token Index: 613

Text #17

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7303. Min Act: -0.1700

Data Index: 5627557 (Open Web Text)

Max Activating Token Index: 724

Text #18

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7315. Min Act: -0.1700

Data Index: 4760311 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 2.9206. Min Range: -2.9206

Max Act: 2.7444. Min Act: -0.1700

Data Index: 6915013 (Open Web Text)

Max Activating Token Index: 504