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

Dataset: Open Web Text

Neuron 1259 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: 1.7771. Min Range: -1.7771

Max Act: 1.7734. Min Act: -0.1700

Data Index: 2114434 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7771. Min Act: -0.1700

Data Index: 6239739 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7531. Min Act: -0.1700

Data Index: 566748 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7029. Min Act: -0.1700

Data Index: 5788568 (Open Web Text)

Max Activating Token Index: 224

Text #4

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7049. Min Act: -0.1700

Data Index: 2817139 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6951. Min Act: -0.1700

Data Index: 6122079 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6492. Min Act: -0.1700

Data Index: 1774032 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6555. Min Act: -0.1700

Data Index: 5717511 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6510. Min Act: -0.1700

Data Index: 7964405 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6355. Min Act: -0.1700

Data Index: 1123282 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6450. Min Act: -0.1700

Data Index: 3941786 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6463. Min Act: -0.1700

Data Index: 4530549 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6201. Min Act: -0.1700

Data Index: 7882741 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6333. Min Act: -0.1700

Data Index: 985267 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6306. Min Act: -0.1700

Data Index: 3367124 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6296. Min Act: -0.1700

Data Index: 2922944 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6221. Min Act: -0.1700

Data Index: 6616339 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6278. Min Act: -0.1700

Data Index: 143437 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6185. Min Act: -0.1699

Data Index: 557617 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.6028. Min Act: -0.1700

Data Index: 3501438 (Open Web Text)

Max Activating Token Index: 866