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

Dataset: Open Web Text

Neuron 904 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: 3.2094. Min Range: -3.2094

Max Act: 3.2094. Min Act: -0.1700

Data Index: 7610220 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.2028. Min Act: -0.1700

Data Index: 4257826 (Open Web Text)

Max Activating Token Index: 559

Text #2

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1960. Min Act: -0.1700

Data Index: 7660457 (Open Web Text)

Max Activating Token Index: 635

Text #3

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1968. Min Act: -0.1700

Data Index: 715194 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1856. Min Act: -0.1700

Data Index: 3974475 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1798. Min Act: -0.1700

Data Index: 8510550 (Open Web Text)

Max Activating Token Index: 575

Text #6

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1451. Min Act: -0.1700

Data Index: 7945386 (Open Web Text)

Max Activating Token Index: 100

Text #7

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1377. Min Act: -0.1700

Data Index: 3205022 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1541. Min Act: -0.1700

Data Index: 7392543 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1397. Min Act: -0.1700

Data Index: 1774787 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1234. Min Act: -0.1700

Data Index: 4405909 (Open Web Text)

Max Activating Token Index: 479

Text #11

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1366. Min Act: -0.1699

Data Index: 4389049 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1169. Min Act: -0.1700

Data Index: 234180 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1117. Min Act: -0.1700

Data Index: 7343704 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1212. Min Act: -0.1700

Data Index: 2682460 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1052. Min Act: -0.1700

Data Index: 8165858 (Open Web Text)

Max Activating Token Index: 880

Text #16

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0934. Min Act: -0.1698

Data Index: 6500628 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1027. Min Act: -0.1700

Data Index: 6456861 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0963. Min Act: -0.1700

Data Index: 544361 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1092. Min Act: -0.1700

Data Index: 5590317 (Open Web Text)

Max Activating Token Index: 66