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

Dataset: Open Web Text

Neuron 1039 in Layer 0

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: 4.5096. Min Range: -4.5096

Max Act: 4.5096. Min Act: -0.1700

Data Index: 2994512 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.4559. Min Act: -0.1700

Data Index: 4420121 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.4199. Min Act: -0.1700

Data Index: 4109986 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.4262. Min Act: -0.1700

Data Index: 2584174 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.4445. Min Act: -0.1700

Data Index: 1426786 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.4156. Min Act: -0.1700

Data Index: 7867934 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3973. Min Act: -0.1700

Data Index: 4799816 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.4087. Min Act: -0.1700

Data Index: 1669689 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3796. Min Act: -0.1700

Data Index: 8378470 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3968. Min Act: -0.1700

Data Index: 6843201 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3491. Min Act: -0.1700

Data Index: 7536944 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3636. Min Act: -0.1700

Data Index: 8766268 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3518. Min Act: -0.1700

Data Index: 2715503 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3524. Min Act: -0.1700

Data Index: 2694137 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3574. Min Act: -0.1700

Data Index: 6643594 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3590. Min Act: -0.1700

Data Index: 5890335 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3238. Min Act: -0.1700

Data Index: 677952 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3519. Min Act: -0.1700

Data Index: 3994752 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3278. Min Act: -0.1700

Data Index: 1774908 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.5096. Min Range: -4.5096

Max Act: 4.3414. Min Act: -0.1700

Data Index: 1807643 (Open Web Text)

Max Activating Token Index: 6