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

Dataset: Open Web Text

Neuron 2106 in Layer 5

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: 4.4013. Min Range: -4.4013

Max Act: 4.4013. Min Act: -0.1700

Data Index: 54214 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.3467. Min Act: -0.1700

Data Index: 2371769 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.2228. Min Act: -0.1700

Data Index: 4143480 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.1461. Min Act: -0.1700

Data Index: 396890 (Open Web Text)

Max Activating Token Index: 343

Text #4

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.1400. Min Act: -0.1700

Data Index: 5302610 (Open Web Text)

Max Activating Token Index: 107

Text #5

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.1384. Min Act: -0.1700

Data Index: 2080244 (Open Web Text)

Max Activating Token Index: 323

Text #6

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.1147. Min Act: -0.1700

Data Index: 1297565 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.1133. Min Act: -0.1700

Data Index: 7946274 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0876. Min Act: -0.1700

Data Index: 3475934 (Open Web Text)

Max Activating Token Index: 1008

Text #9

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0951. Min Act: -0.1700

Data Index: 3443415 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0500. Min Act: -0.1700

Data Index: 2941655 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0651. Min Act: -0.1700

Data Index: 7248290 (Open Web Text)

Max Activating Token Index: 301

Text #12

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0851. Min Act: -0.1700

Data Index: 5641247 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0711. Min Act: -0.1700

Data Index: 2730396 (Open Web Text)

Max Activating Token Index: 118

Text #14

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0783. Min Act: -0.1700

Data Index: 8728360 (Open Web Text)

Max Activating Token Index: 111

Text #15

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0610. Min Act: -0.1700

Data Index: 4076338 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0677. Min Act: -0.1700

Data Index: 2025938 (Open Web Text)

Max Activating Token Index: 319

Text #17

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0643. Min Act: -0.1700

Data Index: 1327270 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0807. Min Act: -0.1700

Data Index: 610863 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 4.4013. Min Range: -4.4013

Max Act: 4.0562. Min Act: -0.1700

Data Index: 463480 (Open Web Text)

Max Activating Token Index: 704