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

Dataset: Open Web Text

Neuron 1415 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: 3.8214. Min Range: -3.8214

Max Act: 3.8214. Min Act: -0.1700

Data Index: 3368832 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.8006. Min Act: -0.1700

Data Index: 7863229 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.8070. Min Act: -0.1700

Data Index: 6365009 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.7669. Min Act: -0.1700

Data Index: 6631829 (Open Web Text)

Max Activating Token Index: 197

Text #4

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.7548. Min Act: -0.1700

Data Index: 8503751 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.7051. Min Act: -0.1700

Data Index: 4536279 (Open Web Text)

Max Activating Token Index: 240

Text #6

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.6694. Min Act: -0.1700

Data Index: 8209069 (Open Web Text)

Max Activating Token Index: 758

Text #7

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.6381. Min Act: -0.1700

Data Index: 555259 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.6432. Min Act: -0.1700

Data Index: 3876702 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5873. Min Act: -0.1700

Data Index: 3052313 (Open Web Text)

Max Activating Token Index: 239

Text #10

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5969. Min Act: -0.1700

Data Index: 2232731 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5941. Min Act: -0.1700

Data Index: 7136743 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.6218. Min Act: -0.1700

Data Index: 4099823 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.6086. Min Act: -0.1700

Data Index: 6062420 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.6158. Min Act: -0.1700

Data Index: 6607158 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5925. Min Act: -0.1700

Data Index: 1575845 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5753. Min Act: -0.1700

Data Index: 6604117 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5527. Min Act: -0.1700

Data Index: 7144518 (Open Web Text)

Max Activating Token Index: 748

Text #18

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5865. Min Act: -0.1700

Data Index: 3820338 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 3.8214. Min Range: -3.8214

Max Act: 3.5703. Min Act: -0.1700

Data Index: 987506 (Open Web Text)

Max Activating Token Index: 490