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

Dataset: Open Web Text

Neuron 1734 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: 3.5085. Min Range: -3.5085

Max Act: 3.5047. Min Act: -0.1700

Data Index: 4695870 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.5085. Min Act: -0.1700

Data Index: 1675146 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4983. Min Act: -0.1700

Data Index: 5797165 (Open Web Text)

Max Activating Token Index: 860

Text #3

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4720. Min Act: -0.1700

Data Index: 4810089 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4881. Min Act: -0.1700

Data Index: 5265055 (Open Web Text)

Max Activating Token Index: 543

Text #5

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4602. Min Act: -0.1700

Data Index: 2802891 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4549. Min Act: -0.1700

Data Index: 3934946 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4419. Min Act: -0.1700

Data Index: 5797166 (Open Web Text)

Max Activating Token Index: 731

Text #8

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4451. Min Act: -0.1700

Data Index: 8574029 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4217. Min Act: -0.1700

Data Index: 3918670 (Open Web Text)

Max Activating Token Index: 355

Text #10

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4472. Min Act: -0.1700

Data Index: 4827953 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4244. Min Act: -0.1700

Data Index: 4810091 (Open Web Text)

Max Activating Token Index: 133

Text #12

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3894. Min Act: -0.1700

Data Index: 8212139 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3875. Min Act: -0.1700

Data Index: 404839 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3527. Min Act: -0.1700

Data Index: 8378777 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4174. Min Act: -0.1700

Data Index: 3127430 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3755. Min Act: -0.1700

Data Index: 4198869 (Open Web Text)

Max Activating Token Index: 119

Text #17

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3707. Min Act: -0.1700

Data Index: 5797167 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3415. Min Act: -0.1700

Data Index: 1793825 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3617. Min Act: -0.1700

Data Index: 7034099 (Open Web Text)

Max Activating Token Index: 487