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

Dataset: Open Web Text

Neuron 2356 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: 3.6404. Min Range: -3.6404

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1663908 (Open Web Text)

Max Activating Token Index: 482

Text #1

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.6036. Min Act: -0.1700

Data Index: 1490078 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5744. Min Act: -0.1700

Data Index: 4410075 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5628. Min Act: -0.1700

Data Index: 1565304 (Open Web Text)

Max Activating Token Index: 152

Text #4

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5500. Min Act: -0.1700

Data Index: 4890308 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5742. Min Act: -0.1700

Data Index: 8121594 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5046. Min Act: -0.1700

Data Index: 4959031 (Open Web Text)

Max Activating Token Index: 816

Text #7

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5341. Min Act: -0.1700

Data Index: 4998912 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5245. Min Act: -0.1700

Data Index: 8704786 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5169. Min Act: -0.1700

Data Index: 5782936 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5165. Min Act: -0.1700

Data Index: 189813 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.5119. Min Act: -0.1700

Data Index: 7667142 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4676. Min Act: -0.1700

Data Index: 7498793 (Open Web Text)

Max Activating Token Index: 515

Text #13

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4858. Min Act: -0.1700

Data Index: 6389603 (Open Web Text)

Max Activating Token Index: 730

Text #14

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4679. Min Act: -0.1700

Data Index: 8275727 (Open Web Text)

Max Activating Token Index: 395

Text #15

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4610. Min Act: -0.1700

Data Index: 1196885 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1216175 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4543. Min Act: -0.1700

Data Index: 7063106 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4653. Min Act: -0.1700

Data Index: 5768476 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 3.6404. Min Range: -3.6404

Max Act: 3.4400. Min Act: -0.1700

Data Index: 6719787 (Open Web Text)

Max Activating Token Index: 511