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

Dataset: Open Web Text

Neuron 408 in Layer 2

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: 3.5119. Min Range: -3.5119

Max Act: 3.5119. Min Act: -0.1700

Data Index: 569541 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4534. Min Act: -0.1700

Data Index: 6389936 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4640. Min Act: -0.1700

Data Index: 6995137 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3846. Min Act: -0.1700

Data Index: 3388360 (Open Web Text)

Max Activating Token Index: 804

Text #4

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4403. Min Act: -0.1700

Data Index: 2062081 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4157. Min Act: -0.1700

Data Index: 4267013 (Open Web Text)

Max Activating Token Index: 252

Text #6

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4449. Min Act: -0.1700

Data Index: 2103157 (Open Web Text)

Max Activating Token Index: 493

Text #7

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4054. Min Act: -0.1700

Data Index: 740765 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4197. Min Act: -0.1700

Data Index: 7904618 (Open Web Text)

Max Activating Token Index: 902

Text #9

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4012. Min Act: -0.1700

Data Index: 385695 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3815. Min Act: -0.1700

Data Index: 6637077 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.4062. Min Act: -0.1700

Data Index: 783957 (Open Web Text)

Max Activating Token Index: 341

Text #12

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3526. Min Act: -0.1700

Data Index: 1301232 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3960. Min Act: -0.1700

Data Index: 4498974 (Open Web Text)

Max Activating Token Index: 924

Text #14

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3686. Min Act: -0.1700

Data Index: 8353619 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3787. Min Act: -0.1700

Data Index: 569163 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3681. Min Act: -0.1700

Data Index: 6481040 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3582. Min Act: -0.1700

Data Index: 8051507 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3573. Min Act: -0.1700

Data Index: 3887338 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 3.5119. Min Range: -3.5119

Max Act: 3.3486. Min Act: -0.1700

Data Index: 2924819 (Open Web Text)

Max Activating Token Index: 424