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

Dataset: Open Web Text

Neuron 2900 in Layer 1

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: 1.9257. Min Range: -1.9257

Max Act: 1.9257. Min Act: -0.1700

Data Index: 5352631 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8887. Min Act: -0.1700

Data Index: 812298 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8697. Min Act: -0.1700

Data Index: 6039575 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8637. Min Act: -0.1700

Data Index: 1512319 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8444. Min Act: -0.1700

Data Index: 3616537 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8526. Min Act: -0.1700

Data Index: 7109158 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8359. Min Act: -0.1700

Data Index: 7850143 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8448. Min Act: -0.1700

Data Index: 533560 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8311. Min Act: -0.1700

Data Index: 1536003 (Open Web Text)

Max Activating Token Index: 638

Text #9

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8132. Min Act: -0.1700

Data Index: 1715262 (Open Web Text)

Max Activating Token Index: 699

Text #10

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8119. Min Act: -0.1700

Data Index: 6291043 (Open Web Text)

Max Activating Token Index: 767

Text #11

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8141. Min Act: -0.1700

Data Index: 8668172 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8103. Min Act: -0.1700

Data Index: 4385116 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.8070. Min Act: -0.1700

Data Index: 8797071 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7964. Min Act: -0.1700

Data Index: 6331021 (Open Web Text)

Max Activating Token Index: 159

Text #15

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7930. Min Act: -0.1700

Data Index: 4472587 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7981. Min Act: -0.1700

Data Index: 8301592 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7936. Min Act: -0.1700

Data Index: 3575173 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7843. Min Act: -0.1700

Data Index: 8101550 (Open Web Text)

Max Activating Token Index: 168

Text #19

Max Range: 1.9257. Min Range: -1.9257

Max Act: 1.7819. Min Act: -0.1700

Data Index: 3117686 (Open Web Text)

Max Activating Token Index: 625