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

Dataset: Open Web Text

Neuron 1664 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: 4.1323. Min Range: -4.1323

Max Act: 4.1323. Min Act: -0.1700

Data Index: 535373 (Open Web Text)

Max Activating Token Index: 103

Text #1

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0726. Min Act: -0.1700

Data Index: 2537639 (Open Web Text)

Max Activating Token Index: 346

Text #2

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0879. Min Act: -0.1700

Data Index: 4111897 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0825. Min Act: -0.1700

Data Index: 4722527 (Open Web Text)

Max Activating Token Index: 911

Text #4

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0931. Min Act: -0.1700

Data Index: 127187 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0542. Min Act: -0.1700

Data Index: 3633549 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0457. Min Act: -0.1700

Data Index: 796707 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0437. Min Act: -0.1700

Data Index: 8637018 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0600. Min Act: -0.1700

Data Index: 2741029 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0318. Min Act: -0.1700

Data Index: 5627752 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0372. Min Act: -0.1700

Data Index: 4030934 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0377. Min Act: -0.1700

Data Index: 2103694 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0202. Min Act: -0.1700

Data Index: 2905968 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0223. Min Act: -0.1700

Data Index: 1554266 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0221. Min Act: -0.1700

Data Index: 3366245 (Open Web Text)

Max Activating Token Index: 573

Text #15

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0267. Min Act: -0.1700

Data Index: 3386284 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0157. Min Act: -0.1700

Data Index: 3390658 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0218. Min Act: -0.1700

Data Index: 848649 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0027. Min Act: -0.1700

Data Index: 3422873 (Open Web Text)

Max Activating Token Index: 210

Text #19

Max Range: 4.1323. Min Range: -4.1323

Max Act: 4.0139. Min Act: -0.1700

Data Index: 908726 (Open Web Text)

Max Activating Token Index: 37