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

Dataset: Open Web Text

Neuron 2028 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: 3.1816. Min Range: -3.1816

Max Act: 3.1816. Min Act: -0.1700

Data Index: 8327527 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 3.1816. Min Range: -3.1816

Max Act: 3.0165. Min Act: -0.1700

Data Index: 4897650 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9836. Min Act: -0.1700

Data Index: 7128061 (Open Web Text)

Max Activating Token Index: 831

Text #3

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9845. Min Act: -0.1700

Data Index: 1575064 (Open Web Text)

Max Activating Token Index: 271

Text #4

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9562. Min Act: -0.1700

Data Index: 713591 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9704. Min Act: -0.1700

Data Index: 3001497 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9737. Min Act: -0.1700

Data Index: 5243475 (Open Web Text)

Max Activating Token Index: 683

Text #7

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9506. Min Act: -0.1700

Data Index: 1386203 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9523. Min Act: -0.1700

Data Index: 5430032 (Open Web Text)

Max Activating Token Index: 795

Text #9

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9619. Min Act: -0.1700

Data Index: 1706828 (Open Web Text)

Max Activating Token Index: 76

Text #10

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9592. Min Act: -0.1700

Data Index: 5762060 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9482. Min Act: -0.1700

Data Index: 937513 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9357. Min Act: -0.1700

Data Index: 1357488 (Open Web Text)

Max Activating Token Index: 425

Text #13

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9409. Min Act: -0.1700

Data Index: 763431 (Open Web Text)

Max Activating Token Index: 763

Text #14

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9387. Min Act: -0.1700

Data Index: 6697966 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9310. Min Act: -0.1700

Data Index: 203756 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9584. Min Act: -0.1700

Data Index: 4074797 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9280. Min Act: -0.1700

Data Index: 6795995 (Open Web Text)

Max Activating Token Index: 250

Text #18

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.8942. Min Act: -0.1700

Data Index: 1219633 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 3.1816. Min Range: -3.1816

Max Act: 2.9393. Min Act: -0.1700

Data Index: 5244649 (Open Web Text)

Max Activating Token Index: 17