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

Dataset: Open Web Text

Neuron 1873 in Layer 6

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: 4.2051. Min Range: -4.2051

Max Act: 4.2051. Min Act: -0.1700

Data Index: 5731076 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1604. Min Act: -0.1700

Data Index: 1478317 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1606. Min Act: -0.1700

Data Index: 7239908 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1778. Min Act: -0.1700

Data Index: 4003673 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1238. Min Act: -0.1700

Data Index: 5325412 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1262. Min Act: -0.1700

Data Index: 4085127 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0922. Min Act: -0.1700

Data Index: 2311996 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1069. Min Act: -0.1700

Data Index: 1961384 (Open Web Text)

Max Activating Token Index: 661

Text #8

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.1064. Min Act: -0.1700

Data Index: 4819085 (Open Web Text)

Max Activating Token Index: 853

Text #9

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0762. Min Act: -0.1700

Data Index: 5668850 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0702. Min Act: -0.1700

Data Index: 8012160 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0516. Min Act: -0.1700

Data Index: 7137694 (Open Web Text)

Max Activating Token Index: 245

Text #12

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0835. Min Act: -0.1700

Data Index: 6021099 (Open Web Text)

Max Activating Token Index: 764

Text #13

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0658. Min Act: -0.1700

Data Index: 2353439 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0583. Min Act: -0.1700

Data Index: 3966462 (Open Web Text)

Max Activating Token Index: 631

Text #15

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0969. Min Act: -0.1700

Data Index: 1251319 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0392. Min Act: -0.1700

Data Index: 2702153 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0397. Min Act: -0.1700

Data Index: 1963363 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0565. Min Act: -0.1700

Data Index: 5227026 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 4.2051. Min Range: -4.2051

Max Act: 4.0186. Min Act: -0.1700

Data Index: 6708953 (Open Web Text)

Max Activating Token Index: 601