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

Dataset: Open Web Text

Neuron 2587 in Layer 4

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: 3.8514. Min Range: -3.8514

Max Act: 3.8105. Min Act: -0.1700

Data Index: 776689 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.8254. Min Act: -0.1700

Data Index: 321402 (Open Web Text)

Max Activating Token Index: 405

Text #2

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.8514. Min Act: -0.1700

Data Index: 12436 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.8492. Min Act: -0.1700

Data Index: 4660253 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.8168. Min Act: -0.1700

Data Index: 139161 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7554. Min Act: -0.1700

Data Index: 3325207 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7710. Min Act: -0.1700

Data Index: 1109251 (Open Web Text)

Max Activating Token Index: 493

Text #7

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7703. Min Act: -0.1700

Data Index: 7501828 (Open Web Text)

Max Activating Token Index: 634

Text #8

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7942. Min Act: -0.1700

Data Index: 2711592 (Open Web Text)

Max Activating Token Index: 619

Text #9

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7799. Min Act: -0.1700

Data Index: 2648141 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7612. Min Act: -0.1700

Data Index: 7347219 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7649. Min Act: -0.1700

Data Index: 3515131 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7864. Min Act: -0.1700

Data Index: 5646182 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7513. Min Act: -0.1700

Data Index: 2931323 (Open Web Text)

Max Activating Token Index: 361

Text #14

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7778. Min Act: -0.1700

Data Index: 8756974 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7344. Min Act: -0.1700

Data Index: 7150533 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7259. Min Act: -0.1700

Data Index: 6513162 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7480. Min Act: -0.1700

Data Index: 7779288 (Open Web Text)

Max Activating Token Index: 824

Text #18

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7493. Min Act: -0.1700

Data Index: 346386 (Open Web Text)

Max Activating Token Index: 156

Text #19

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.7367. Min Act: -0.1700

Data Index: 4027986 (Open Web Text)

Max Activating Token Index: 427