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

Dataset: Open Web Text

Neuron 2319 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: 2.3131. Min Range: -2.3131

Max Act: 2.3131. Min Act: -0.1700

Data Index: 4992782 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1879. Min Act: -0.1700

Data Index: 4963603 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1894. Min Act: -0.1700

Data Index: 3384518 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1645. Min Act: -0.1700

Data Index: 7581417 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1559. Min Act: -0.1700

Data Index: 8721071 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1490. Min Act: -0.1700

Data Index: 7833629 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1462. Min Act: -0.1700

Data Index: 2365419 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1483. Min Act: -0.1699

Data Index: 3824106 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1283. Min Act: -0.1700

Data Index: 8341920 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1269. Min Act: -0.1700

Data Index: 1970336 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1182. Min Act: -0.1700

Data Index: 7748047 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1188. Min Act: -0.1700

Data Index: 4669778 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1151. Min Act: -0.1700

Data Index: 7610002 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1269. Min Act: -0.1700

Data Index: 4167727 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1246. Min Act: -0.1700

Data Index: 5276981 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1159. Min Act: -0.1700

Data Index: 4952751 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1183. Min Act: -0.1700

Data Index: 5803496 (Open Web Text)

Max Activating Token Index: 203

Text #17

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1155. Min Act: -0.1700

Data Index: 6426684 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1041. Min Act: -0.1700

Data Index: 6699360 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 2.3131. Min Range: -2.3131

Max Act: 2.1021. Min Act: -0.1700

Data Index: 7345550 (Open Web Text)

Max Activating Token Index: 16