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

Dataset: Open Web Text

Neuron 2927 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: 4.6259. Min Range: -4.6259

Max Act: 4.6259. Min Act: -0.1700

Data Index: 4164215 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3940. Min Act: -0.1700

Data Index: 3186456 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3650. Min Act: -0.1700

Data Index: 385751 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3848. Min Act: -0.1700

Data Index: 3987651 (Open Web Text)

Max Activating Token Index: 984

Text #4

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3497. Min Act: -0.1700

Data Index: 6131994 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2937. Min Act: -0.1700

Data Index: 2541686 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3557. Min Act: -0.1700

Data Index: 5596957 (Open Web Text)

Max Activating Token Index: 833

Text #7

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3361. Min Act: -0.1700

Data Index: 7712201 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3044. Min Act: -0.1700

Data Index: 5300254 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2963. Min Act: -0.1700

Data Index: 4902798 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.3315. Min Act: -0.1700

Data Index: 3623716 (Open Web Text)

Max Activating Token Index: 826

Text #11

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2674. Min Act: -0.1700

Data Index: 3968458 (Open Web Text)

Max Activating Token Index: 887

Text #12

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2799. Min Act: -0.1700

Data Index: 4935888 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2877. Min Act: -0.1700

Data Index: 290173 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2869. Min Act: -0.1700

Data Index: 3232869 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2759. Min Act: -0.1700

Data Index: 5345111 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2369. Min Act: -0.1700

Data Index: 1748599 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2364. Min Act: -0.1700

Data Index: 4622735 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2367. Min Act: -0.1700

Data Index: 2354226 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.2365. Min Act: -0.1700

Data Index: 1079314 (Open Web Text)

Max Activating Token Index: 525