Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5798 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.4549. Min Act: -0.1700

Data Index: 6821529 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.3924. Min Act: -0.1700

Data Index: 1159766 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.3924. Min Act: -0.1700

Data Index: 3102553 (Open Web Text)

Max Activating Token Index: 62

Text #3

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.3299. Min Act: -0.1700

Data Index: 3794026 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.3299. Min Act: -0.1700

Data Index: 1205005 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.2674. Min Act: -0.1700

Data Index: 6375835 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.2049. Min Act: -0.1700

Data Index: 6945992 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.2049. Min Act: -0.1700

Data Index: 4895494 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.2049. Min Act: -0.1700

Data Index: 1206592 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.1736. Min Act: -0.1700

Data Index: 843768 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.1424. Min Act: -0.1700

Data Index: 1878860 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.1424. Min Act: -0.1700

Data Index: 4105692 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.1111. Min Act: -0.1700

Data Index: 6277004 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.1111. Min Act: -0.1700

Data Index: 5535148 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.0799. Min Act: -0.1700

Data Index: 4200618 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.0799. Min Act: -0.1700

Data Index: 3988271 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.0799. Min Act: -0.1700

Data Index: 2144825 (Open Web Text)

Max Activating Token Index: 910

Text #17

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.0486. Min Act: -0.1700

Data Index: 5730352 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.0486. Min Act: -0.1700

Data Index: 4871907 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 7.4549. Min Range: -7.4549

Max Act: 7.0486. Min Act: -0.1700

Data Index: 37122 (Open Web Text)

Max Activating Token Index: 741