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

Dataset: Open Web Text

Neuron 980 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: 5.3123. Min Range: -5.3123

Max Act: 5.3123. Min Act: -0.1700

Data Index: 3978821 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.2769. Min Act: -0.1700

Data Index: 6064319 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.2452. Min Act: -0.1700

Data Index: 5733268 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.2088. Min Act: -0.1700

Data Index: 907576 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.2119. Min Act: -0.1700

Data Index: 2187032 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.2315. Min Act: -0.1700

Data Index: 7767271 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.2072. Min Act: -0.1700

Data Index: 4409094 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1999. Min Act: -0.1700

Data Index: 4409096 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1944. Min Act: -0.1700

Data Index: 3569542 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1739. Min Act: -0.1700

Data Index: 636506 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1322. Min Act: -0.1700

Data Index: 8325306 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1674. Min Act: -0.1700

Data Index: 4535868 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1682. Min Act: -0.1700

Data Index: 3245815 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1509. Min Act: -0.1700

Data Index: 3075763 (Open Web Text)

Max Activating Token Index: 544

Text #14

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1720. Min Act: -0.1700

Data Index: 7813622 (Open Web Text)

Max Activating Token Index: 125

Text #15

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1559. Min Act: -0.1700

Data Index: 7336107 (Open Web Text)

Max Activating Token Index: 825

Text #16

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1617. Min Act: -0.1700

Data Index: 5733270 (Open Web Text)

Max Activating Token Index: 74

Text #17

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1451. Min Act: -0.1700

Data Index: 4848713 (Open Web Text)

Max Activating Token Index: 269

Text #18

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1613. Min Act: -0.1700

Data Index: 4646080 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 5.3123. Min Range: -5.3123

Max Act: 5.1094. Min Act: -0.1700

Data Index: 130052 (Open Web Text)

Max Activating Token Index: 687