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

Dataset: Open Web Text

Neuron 1440 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: 3.2272. Min Range: -3.2272

Max Act: 3.2272. Min Act: -0.1700

Data Index: 4940028 (Open Web Text)

Max Activating Token Index: 757

Text #1

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.2186. Min Act: -0.1700

Data Index: 3640686 (Open Web Text)

Max Activating Token Index: 987

Text #2

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1282. Min Act: -0.1700

Data Index: 7990013 (Open Web Text)

Max Activating Token Index: 914

Text #3

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.1094. Min Act: -0.1700

Data Index: 2109657 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0420. Min Act: -0.1700

Data Index: 3862791 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0101. Min Act: -0.1700

Data Index: 4073519 (Open Web Text)

Max Activating Token Index: 578

Text #6

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0323. Min Act: -0.1700

Data Index: 88906 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9793. Min Act: -0.1700

Data Index: 7734289 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9903. Min Act: -0.1700

Data Index: 6977548 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9953. Min Act: -0.1700

Data Index: 2917953 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9582. Min Act: -0.1700

Data Index: 2563233 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9406. Min Act: -0.1700

Data Index: 5425459 (Open Web Text)

Max Activating Token Index: 1019

Text #12

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9834. Min Act: -0.1700

Data Index: 4122638 (Open Web Text)

Max Activating Token Index: 195

Text #13

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9429. Min Act: -0.1700

Data Index: 5333234 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9562. Min Act: -0.1700

Data Index: 2273432 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9323. Min Act: -0.1700

Data Index: 4671684 (Open Web Text)

Max Activating Token Index: 597

Text #16

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9876. Min Act: -0.1700

Data Index: 8410941 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9716. Min Act: -0.1700

Data Index: 8293093 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 3.2272. Min Range: -3.2272

Max Act: 3.0050. Min Act: -0.1700

Data Index: 8000740 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 3.2272. Min Range: -3.2272

Max Act: 2.9445. Min Act: -0.1700

Data Index: 211105 (Open Web Text)

Max Activating Token Index: 261