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

Dataset: Open Web Text

Neuron 1740 in Layer 1

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: 3.0224. Min Range: -3.0224

Max Act: 3.0223. Min Act: -0.1700

Data Index: 1171457 (Open Web Text)

Max Activating Token Index: 499

Text #1

Max Range: 3.0224. Min Range: -3.0224

Max Act: 3.0224. Min Act: -0.1700

Data Index: 637110 (Open Web Text)

Max Activating Token Index: 1016

Text #2

Max Range: 3.0224. Min Range: -3.0224

Max Act: 3.0092. Min Act: -0.1700

Data Index: 6754937 (Open Web Text)

Max Activating Token Index: 206

Text #3

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9766. Min Act: -0.1700

Data Index: 8497691 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9343. Min Act: -0.1700

Data Index: 1040825 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9424. Min Act: -0.1700

Data Index: 2188713 (Open Web Text)

Max Activating Token Index: 240

Text #6

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9350. Min Act: -0.1700

Data Index: 5257391 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9333. Min Act: -0.1700

Data Index: 5499458 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8975. Min Act: -0.1700

Data Index: 1606107 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9126. Min Act: -0.1700

Data Index: 8361244 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9125. Min Act: -0.1700

Data Index: 5553129 (Open Web Text)

Max Activating Token Index: 127

Text #11

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8862. Min Act: -0.1700

Data Index: 1853850 (Open Web Text)

Max Activating Token Index: 576

Text #12

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8941. Min Act: -0.1700

Data Index: 2234811 (Open Web Text)

Max Activating Token Index: 131

Text #13

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8815. Min Act: -0.1700

Data Index: 7168593 (Open Web Text)

Max Activating Token Index: 138

Text #14

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8955. Min Act: -0.1700

Data Index: 770326 (Open Web Text)

Max Activating Token Index: 280

Text #15

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8823. Min Act: -0.1700

Data Index: 4971443 (Open Web Text)

Max Activating Token Index: 210

Text #16

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8746. Min Act: -0.1700

Data Index: 6167845 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8707. Min Act: -0.1700

Data Index: 4421272 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8660. Min Act: -0.1700

Data Index: 339363 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8613. Min Act: -0.1700

Data Index: 5369707 (Open Web Text)

Max Activating Token Index: 293