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

Dataset: Open Web Text

Neuron 2668 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: 3.0026. Min Range: -3.0026

Max Act: 3.0026. Min Act: -0.1700

Data Index: 5020471 (Open Web Text)

Max Activating Token Index: 273

Text #1

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9374. Min Act: -0.1700

Data Index: 7162028 (Open Web Text)

Max Activating Token Index: 821

Text #2

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.9487. Min Act: -0.1700

Data Index: 2181555 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8800. Min Act: -0.1700

Data Index: 708039 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8907. Min Act: -0.1700

Data Index: 131987 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8659. Min Act: -0.1700

Data Index: 4810996 (Open Web Text)

Max Activating Token Index: 925

Text #6

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8411. Min Act: -0.1700

Data Index: 1551549 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8527. Min Act: -0.1700

Data Index: 2970202 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8365. Min Act: -0.1700

Data Index: 78634 (Open Web Text)

Max Activating Token Index: 356

Text #9

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8256. Min Act: -0.1700

Data Index: 8470491 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8404. Min Act: -0.1700

Data Index: 4811860 (Open Web Text)

Max Activating Token Index: 411

Text #11

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8338. Min Act: -0.1700

Data Index: 4811832 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8050. Min Act: -0.1700

Data Index: 7429144 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8181. Min Act: -0.1700

Data Index: 6819322 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.8012. Min Act: -0.1700

Data Index: 1376314 (Open Web Text)

Max Activating Token Index: 100

Text #15

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.7847. Min Act: -0.1700

Data Index: 4604932 (Open Web Text)

Max Activating Token Index: 364

Text #16

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.7794. Min Act: -0.1700

Data Index: 2970199 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.7827. Min Act: -0.1700

Data Index: 1046007 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.7832. Min Act: -0.1700

Data Index: 1947911 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 3.0026. Min Range: -3.0026

Max Act: 2.7987. Min Act: -0.1700

Data Index: 2662628 (Open Web Text)

Max Activating Token Index: 473