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

Dataset: Open Web Text

Neuron 2918 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: 3.9181. Min Range: -3.9181

Max Act: 3.9181. Min Act: -0.1700

Data Index: 5782092 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.8374. Min Act: -0.1700

Data Index: 4616769 (Open Web Text)

Max Activating Token Index: 563

Text #2

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.8063. Min Act: -0.1700

Data Index: 5673691 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7929. Min Act: -0.1700

Data Index: 3709005 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.8066. Min Act: -0.1700

Data Index: 2576413 (Open Web Text)

Max Activating Token Index: 983

Text #5

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7500. Min Act: -0.1700

Data Index: 6971824 (Open Web Text)

Max Activating Token Index: 503

Text #6

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7251. Min Act: -0.1700

Data Index: 167065 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6934. Min Act: -0.1700

Data Index: 7829495 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7150. Min Act: -0.1700

Data Index: 1126864 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7241. Min Act: -0.1700

Data Index: 6450777 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7293. Min Act: -0.1700

Data Index: 2976659 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7196. Min Act: -0.1700

Data Index: 638289 (Open Web Text)

Max Activating Token Index: 719

Text #12

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6522. Min Act: -0.1700

Data Index: 4339376 (Open Web Text)

Max Activating Token Index: 953

Text #13

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6853. Min Act: -0.1700

Data Index: 151378 (Open Web Text)

Max Activating Token Index: 300

Text #14

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.7013. Min Act: -0.1700

Data Index: 6574453 (Open Web Text)

Max Activating Token Index: 602

Text #15

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6480. Min Act: -0.1700

Data Index: 975486 (Open Web Text)

Max Activating Token Index: 116

Text #16

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6756. Min Act: -0.1700

Data Index: 2747563 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6513. Min Act: -0.1700

Data Index: 8480799 (Open Web Text)

Max Activating Token Index: 786

Text #18

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6642. Min Act: -0.1700

Data Index: 497991 (Open Web Text)

Max Activating Token Index: 926

Text #19

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6439. Min Act: -0.1700

Data Index: 8813096 (Open Web Text)

Max Activating Token Index: 262