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

Dataset: Open Web Text

Neuron 2834 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: 1.4261. Min Range: -1.4261

Max Act: 1.4261. Min Act: -0.1675

Data Index: 7044195 (Open Web Text)

Max Activating Token Index: 182

Text #1

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3933. Min Act: -0.1672

Data Index: 7044194 (Open Web Text)

Max Activating Token Index: 296

Text #2

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3669. Min Act: -0.1700

Data Index: 6107134 (Open Web Text)

Max Activating Token Index: 363

Text #3

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3563. Min Act: -0.1672

Data Index: 7044193 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3413. Min Act: -0.1700

Data Index: 1846054 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3505. Min Act: -0.1700

Data Index: 610480 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3444. Min Act: -0.1697

Data Index: 7044192 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3099. Min Act: -0.1699

Data Index: 7044201 (Open Web Text)

Max Activating Token Index: 140

Text #8

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3030. Min Act: -0.1700

Data Index: 3088047 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.3031. Min Act: -0.1700

Data Index: 7502169 (Open Web Text)

Max Activating Token Index: 742

Text #10

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2944. Min Act: -0.1699

Data Index: 7709163 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2791. Min Act: -0.1700

Data Index: 8211745 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2742. Min Act: -0.1700

Data Index: 35861 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2697. Min Act: -0.1700

Data Index: 2266786 (Open Web Text)

Max Activating Token Index: 431

Text #14

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2642. Min Act: -0.1700

Data Index: 7813695 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2686. Min Act: -0.1699

Data Index: 7044199 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2675. Min Act: -0.1700

Data Index: 5106539 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2565. Min Act: -0.1694

Data Index: 7044202 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2617. Min Act: -0.1700

Data Index: 2016082 (Open Web Text)

Max Activating Token Index: 564

Text #19

Max Range: 1.4261. Min Range: -1.4261

Max Act: 1.2597. Min Act: -0.1700

Data Index: 898552 (Open Web Text)

Max Activating Token Index: 512