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

Dataset: Open Web Text

Neuron 480 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: 3.5287. Min Range: -3.5287

Max Act: 3.5127. Min Act: -0.1700

Data Index: 8399261 (Open Web Text)

Max Activating Token Index: 274

Text #1

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.5287. Min Act: -0.1700

Data Index: 2583626 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.4484. Min Act: -0.1700

Data Index: 1699658 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.3593. Min Act: -0.1700

Data Index: 3175107 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.3709. Min Act: -0.1700

Data Index: 1467244 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.3436. Min Act: -0.1700

Data Index: 392738 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.3091. Min Act: -0.1700

Data Index: 3789995 (Open Web Text)

Max Activating Token Index: 814

Text #7

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1699063 (Open Web Text)

Max Activating Token Index: 755

Text #8

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2812. Min Act: -0.1700

Data Index: 5647430 (Open Web Text)

Max Activating Token Index: 980

Text #9

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.3115. Min Act: -0.1700

Data Index: 2619864 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2888. Min Act: -0.1700

Data Index: 2681947 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2536. Min Act: -0.1700

Data Index: 2155759 (Open Web Text)

Max Activating Token Index: 154

Text #12

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2705. Min Act: -0.1700

Data Index: 4008883 (Open Web Text)

Max Activating Token Index: 885

Text #13

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2093. Min Act: -0.1700

Data Index: 2525927 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.2166. Min Act: -0.1700

Data Index: 2896758 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.1737. Min Act: -0.1700

Data Index: 3577065 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.1852. Min Act: -0.1700

Data Index: 5647431 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.1750. Min Act: -0.1700

Data Index: 6251789 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.1630. Min Act: -0.1700

Data Index: 2801250 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 3.5287. Min Range: -3.5287

Max Act: 3.1631. Min Act: -0.1700

Data Index: 7926703 (Open Web Text)

Max Activating Token Index: 681