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

Dataset: Open Web Text

Neuron 1846 in Layer 5

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: 3.4496. Min Range: -3.4496

Max Act: 3.4496. Min Act: -0.1700

Data Index: 4089841 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.3290. Min Act: -0.1700

Data Index: 6349273 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.3257. Min Act: -0.1700

Data Index: 8411663 (Open Web Text)

Max Activating Token Index: 46

Text #3

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.3092. Min Act: -0.1700

Data Index: 5912252 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.3053. Min Act: -0.1700

Data Index: 5076047 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2686. Min Act: -0.1700

Data Index: 7098402 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2696. Min Act: -0.1700

Data Index: 244097 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2684. Min Act: -0.1700

Data Index: 2896880 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2575. Min Act: -0.1700

Data Index: 6003013 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2705. Min Act: -0.1700

Data Index: 8417417 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2402. Min Act: -0.1700

Data Index: 8819960 (Open Web Text)

Max Activating Token Index: 300

Text #11

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2484. Min Act: -0.1700

Data Index: 1325374 (Open Web Text)

Max Activating Token Index: 826

Text #12

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2491. Min Act: -0.1700

Data Index: 7126423 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2161. Min Act: -0.1700

Data Index: 5177749 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.1998. Min Act: -0.1700

Data Index: 8502338 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.1893. Min Act: -0.1700

Data Index: 2804601 (Open Web Text)

Max Activating Token Index: 397

Text #16

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.2206. Min Act: -0.1700

Data Index: 1267478 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.1573. Min Act: -0.1700

Data Index: 2897709 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.1536. Min Act: -0.1700

Data Index: 6848796 (Open Web Text)

Max Activating Token Index: 292

Text #19

Max Range: 3.4496. Min Range: -3.4496

Max Act: 3.1432. Min Act: -0.1700

Data Index: 917060 (Open Web Text)

Max Activating Token Index: 304