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

Dataset: Open Web Text

Neuron 2193 in Layer 6

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: 4.2591. Min Range: -4.2591

Max Act: 4.2591. Min Act: -0.1700

Data Index: 3053552 (Open Web Text)

Max Activating Token Index: 726

Text #1

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1744. Min Act: -0.1700

Data Index: 1261746 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1487. Min Act: -0.1700

Data Index: 3390940 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1242. Min Act: -0.1700

Data Index: 8163650 (Open Web Text)

Max Activating Token Index: 48

Text #4

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1455. Min Act: -0.1700

Data Index: 3323186 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.1052. Min Act: -0.1700

Data Index: 7359489 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0704. Min Act: -0.1700

Data Index: 2453036 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0974. Min Act: -0.1700

Data Index: 2438705 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0744. Min Act: -0.1700

Data Index: 1333467 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0304. Min Act: -0.1700

Data Index: 792561 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0024. Min Act: -0.1700

Data Index: 2986405 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0102. Min Act: -0.1700

Data Index: 1137483 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0172. Min Act: -0.1700

Data Index: 6555180 (Open Web Text)

Max Activating Token Index: 684

Text #13

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0232. Min Act: -0.1700

Data Index: 3680094 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0117. Min Act: -0.1700

Data Index: 5169167 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 4.2591. Min Range: -4.2591

Max Act: 3.9942. Min Act: -0.1700

Data Index: 238499 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 4.2591. Min Range: -4.2591

Max Act: 3.9781. Min Act: -0.1700

Data Index: 166815 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 4.2591. Min Range: -4.2591

Max Act: 3.9978. Min Act: -0.1700

Data Index: 478084 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 4.2591. Min Range: -4.2591

Max Act: 4.0156. Min Act: -0.1700

Data Index: 4363181 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 4.2591. Min Range: -4.2591

Max Act: 3.9678. Min Act: -0.1700

Data Index: 1896190 (Open Web Text)

Max Activating Token Index: 810