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

Dataset: Open Web Text

Neuron 1299 in Layer 6

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: 3.8425. Min Range: -3.8425

Max Act: 3.8425. Min Act: -0.1700

Data Index: 2505122 (Open Web Text)

Max Activating Token Index: 438

Text #1

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.8045. Min Act: -0.1700

Data Index: 7888577 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.8175. Min Act: -0.1700

Data Index: 826087 (Open Web Text)

Max Activating Token Index: 840

Text #3

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7738. Min Act: -0.1700

Data Index: 5203815 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7645. Min Act: -0.1700

Data Index: 7492509 (Open Web Text)

Max Activating Token Index: 478

Text #5

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7531. Min Act: -0.1700

Data Index: 1615518 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7401. Min Act: -0.1700

Data Index: 2227034 (Open Web Text)

Max Activating Token Index: 499

Text #7

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7226. Min Act: -0.1700

Data Index: 227227 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7472. Min Act: -0.1700

Data Index: 7404814 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7064. Min Act: -0.1700

Data Index: 3898287 (Open Web Text)

Max Activating Token Index: 671

Text #10

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7460. Min Act: -0.1700

Data Index: 5181058 (Open Web Text)

Max Activating Token Index: 809

Text #11

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7085. Min Act: -0.1700

Data Index: 339004 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7077. Min Act: -0.1700

Data Index: 5657086 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7218. Min Act: -0.1700

Data Index: 6466274 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6861. Min Act: -0.1700

Data Index: 3749462 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.7008. Min Act: -0.1700

Data Index: 7477408 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6953. Min Act: -0.1700

Data Index: 1985282 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6880. Min Act: -0.1700

Data Index: 2148813 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6850. Min Act: -0.1700

Data Index: 1936937 (Open Web Text)

Max Activating Token Index: 986

Text #19

Max Range: 3.8425. Min Range: -3.8425

Max Act: 3.6661. Min Act: -0.1700

Data Index: 404505 (Open Web Text)

Max Activating Token Index: 334