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

Dataset: Open Web Text

Neuron 266 in Layer 3

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: 3.9948. Min Range: -3.9948

Max Act: 3.9837. Min Act: -0.1700

Data Index: 1501146 (Open Web Text)

Max Activating Token Index: 978

Text #1

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9948. Min Act: -0.1700

Data Index: 4853161 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9897. Min Act: -0.1700

Data Index: 5200491 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9568. Min Act: -0.1700

Data Index: 4631109 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9289. Min Act: -0.1700

Data Index: 8153793 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9547. Min Act: -0.1700

Data Index: 7533745 (Open Web Text)

Max Activating Token Index: 803

Text #6

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9412. Min Act: -0.1700

Data Index: 1605240 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9503. Min Act: -0.1700

Data Index: 1207272 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9454. Min Act: -0.1700

Data Index: 1668071 (Open Web Text)

Max Activating Token Index: 151

Text #9

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9677. Min Act: -0.1700

Data Index: 1419750 (Open Web Text)

Max Activating Token Index: 166

Text #10

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9299. Min Act: -0.1700

Data Index: 5177804 (Open Web Text)

Max Activating Token Index: 830

Text #11

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9113. Min Act: -0.1700

Data Index: 3822974 (Open Web Text)

Max Activating Token Index: 166

Text #12

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9018. Min Act: -0.1700

Data Index: 7189136 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9224. Min Act: -0.1700

Data Index: 6400928 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.8818. Min Act: -0.1700

Data Index: 6167213 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9229. Min Act: -0.1700

Data Index: 4785515 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9197. Min Act: -0.1700

Data Index: 858746 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9042. Min Act: -0.1700

Data Index: 2732300 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9276. Min Act: -0.1700

Data Index: 2585899 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 3.9948. Min Range: -3.9948

Max Act: 3.9096. Min Act: -0.1700

Data Index: 2275630 (Open Web Text)

Max Activating Token Index: 473