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

Dataset: Open Web Text

Neuron 2538 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: 5.0276. Min Range: -5.0276

Max Act: 5.0276. Min Act: -0.1700

Data Index: 2852511 (Open Web Text)

Max Activating Token Index: 986

Text #1

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.9059. Min Act: -0.1700

Data Index: 2281225 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.8132. Min Act: -0.1700

Data Index: 5896595 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.8097. Min Act: -0.1700

Data Index: 2976507 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.8164. Min Act: -0.1700

Data Index: 4008060 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.8157. Min Act: -0.1700

Data Index: 3915236 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.7658. Min Act: -0.1700

Data Index: 8644369 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.7925. Min Act: -0.1700

Data Index: 4755779 (Open Web Text)

Max Activating Token Index: 617

Text #8

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.7574. Min Act: -0.1700

Data Index: 6538645 (Open Web Text)

Max Activating Token Index: 747

Text #9

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6384. Min Act: -0.1700

Data Index: 1461390 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.7029. Min Act: -0.1700

Data Index: 8727766 (Open Web Text)

Max Activating Token Index: 964

Text #11

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.7082. Min Act: -0.1700

Data Index: 6531100 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6703. Min Act: -0.1700

Data Index: 4008061 (Open Web Text)

Max Activating Token Index: 623

Text #13

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6887. Min Act: -0.1700

Data Index: 2152922 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6382. Min Act: -0.1700

Data Index: 3230845 (Open Web Text)

Max Activating Token Index: 525

Text #15

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6351. Min Act: -0.1700

Data Index: 1649200 (Open Web Text)

Max Activating Token Index: 317

Text #16

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6553. Min Act: -0.1700

Data Index: 5902260 (Open Web Text)

Max Activating Token Index: 135

Text #17

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6040. Min Act: -0.1700

Data Index: 97297 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.5564. Min Act: -0.1700

Data Index: 2400719 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6496. Min Act: -0.1700

Data Index: 5311991 (Open Web Text)

Max Activating Token Index: 734