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

Dataset: Open Web Text

Neuron 2035 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: 1.0992. Min Range: -1.0992

Max Act: 1.0992. Min Act: -0.1700

Data Index: 408887 (Open Web Text)

Max Activating Token Index: 877

Text #1

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0966. Min Act: -0.1700

Data Index: 6508988 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0400. Min Act: -0.1700

Data Index: 3951738 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0193. Min Act: -0.1700

Data Index: 2835024 (Open Web Text)

Max Activating Token Index: 933

Text #4

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0132. Min Act: -0.1700

Data Index: 5627811 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0043. Min Act: -0.1700

Data Index: 4520102 (Open Web Text)

Max Activating Token Index: 579

Text #6

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0016. Min Act: -0.1700

Data Index: 5500541 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 1.0992. Min Range: -1.0992

Max Act: 1.0027. Min Act: -0.1700

Data Index: 5152439 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9986. Min Act: -0.1700

Data Index: 1591909 (Open Web Text)

Max Activating Token Index: 699

Text #9

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9907. Min Act: -0.1700

Data Index: 1956498 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9957. Min Act: -0.1700

Data Index: 5798479 (Open Web Text)

Max Activating Token Index: 892

Text #11

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9902. Min Act: -0.1700

Data Index: 7075045 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9851. Min Act: -0.1700

Data Index: 8800561 (Open Web Text)

Max Activating Token Index: 854

Text #13

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9854. Min Act: -0.1700

Data Index: 3862301 (Open Web Text)

Max Activating Token Index: 913

Text #14

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9898. Min Act: -0.1700

Data Index: 5639596 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9836. Min Act: -0.1700

Data Index: 8339582 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9880. Min Act: -0.1700

Data Index: 3384398 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9852. Min Act: -0.1700

Data Index: 4868315 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9755. Min Act: -0.1700

Data Index: 1800277 (Open Web Text)

Max Activating Token Index: 862

Text #19

Max Range: 1.0992. Min Range: -1.0992

Max Act: 0.9771. Min Act: -0.1700

Data Index: 1998444 (Open Web Text)

Max Activating Token Index: 952