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

Dataset: Open Web Text

Neuron 1028 in Layer 2

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: 3.8398. Min Range: -3.8398

Max Act: 3.8398. Min Act: -0.1700

Data Index: 1394505 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.6737. Min Act: -0.1700

Data Index: 3298790 (Open Web Text)

Max Activating Token Index: 820

Text #2

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.7153. Min Act: -0.1700

Data Index: 271677 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.7070. Min Act: -0.1700

Data Index: 1040122 (Open Web Text)

Max Activating Token Index: 271

Text #4

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.6759. Min Act: -0.1700

Data Index: 6808444 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.6648. Min Act: -0.1700

Data Index: 7467162 (Open Web Text)

Max Activating Token Index: 958

Text #6

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.6710. Min Act: -0.1700

Data Index: 3709306 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4848. Min Act: -0.1700

Data Index: 5533201 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.5349. Min Act: -0.1700

Data Index: 2134898 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.5145. Min Act: -0.1700

Data Index: 6445155 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.5243. Min Act: -0.1700

Data Index: 3938985 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4607. Min Act: -0.1700

Data Index: 3803096 (Open Web Text)

Max Activating Token Index: 803

Text #12

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.5080. Min Act: -0.1700

Data Index: 1521269 (Open Web Text)

Max Activating Token Index: 232

Text #13

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.5085. Min Act: -0.1700

Data Index: 5119875 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4987. Min Act: -0.1700

Data Index: 3231762 (Open Web Text)

Max Activating Token Index: 898

Text #15

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4503. Min Act: -0.1700

Data Index: 6512313 (Open Web Text)

Max Activating Token Index: 993

Text #16

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4954. Min Act: -0.1700

Data Index: 5746992 (Open Web Text)

Max Activating Token Index: 453

Text #17

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4350. Min Act: -0.1700

Data Index: 5264151 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.5331. Min Act: -0.1700

Data Index: 1754253 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 3.8398. Min Range: -3.8398

Max Act: 3.4816. Min Act: -0.1700

Data Index: 5098075 (Open Web Text)

Max Activating Token Index: 503