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

Dataset: Open Web Text

Neuron 695 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: 3.7923. Min Range: -3.7923

Max Act: 3.7923. Min Act: -0.1700

Data Index: 8577927 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7433. Min Act: -0.1700

Data Index: 6305973 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7471. Min Act: -0.1700

Data Index: 4734866 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7089. Min Act: -0.1700

Data Index: 1687202 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7337. Min Act: -0.1700

Data Index: 310598 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7342. Min Act: -0.1700

Data Index: 6754676 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7164. Min Act: -0.1700

Data Index: 2025500 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.7311. Min Act: -0.1700

Data Index: 7855985 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6680. Min Act: -0.1700

Data Index: 4385949 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6956. Min Act: -0.1700

Data Index: 5900027 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6943. Min Act: -0.1700

Data Index: 4049228 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6465. Min Act: -0.1700

Data Index: 2201859 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6592. Min Act: -0.1700

Data Index: 2916230 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6637. Min Act: -0.1700

Data Index: 1330717 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6431. Min Act: -0.1700

Data Index: 7015269 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6237. Min Act: -0.1700

Data Index: 4691041 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6250. Min Act: -0.1700

Data Index: 4973518 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6170. Min Act: -0.1700

Data Index: 6123057 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6395. Min Act: -0.1700

Data Index: 4126261 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.7923. Min Range: -3.7923

Max Act: 3.6176. Min Act: -0.1700

Data Index: 3923533 (Open Web Text)

Max Activating Token Index: 4