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

Dataset: Open Web Text

Neuron 257 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: 4.4689. Min Range: -4.4689

Max Act: 4.4689. Min Act: -0.1700

Data Index: 3556776 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.3994. Min Act: -0.1700

Data Index: 1884503 (Open Web Text)

Max Activating Token Index: 811

Text #2

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.3269. Min Act: -0.1700

Data Index: 5079875 (Open Web Text)

Max Activating Token Index: 347

Text #3

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.2595. Min Act: -0.1700

Data Index: 4221980 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.2168. Min Act: -0.1700

Data Index: 4555262 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.2044. Min Act: -0.1700

Data Index: 5101236 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1870. Min Act: -0.1700

Data Index: 1189043 (Open Web Text)

Max Activating Token Index: 648

Text #7

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.2001. Min Act: -0.1700

Data Index: 4212562 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1579. Min Act: -0.1700

Data Index: 159596 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1200. Min Act: -0.1700

Data Index: 4093857 (Open Web Text)

Max Activating Token Index: 771

Text #10

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.2176. Min Act: -0.1700

Data Index: 2891844 (Open Web Text)

Max Activating Token Index: 838

Text #11

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1322. Min Act: -0.1700

Data Index: 3851231 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1620. Min Act: -0.1700

Data Index: 827265 (Open Web Text)

Max Activating Token Index: 168

Text #13

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1884. Min Act: -0.1700

Data Index: 5376893 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1621. Min Act: -0.1700

Data Index: 2847042 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.2223. Min Act: -0.1700

Data Index: 2455221 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1446. Min Act: -0.1700

Data Index: 2575721 (Open Web Text)

Max Activating Token Index: 169

Text #17

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1515. Min Act: -0.1700

Data Index: 4602095 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1359. Min Act: -0.1700

Data Index: 4502312 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 4.4689. Min Range: -4.4689

Max Act: 4.1510. Min Act: -0.1700

Data Index: 4073086 (Open Web Text)

Max Activating Token Index: 207