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

Dataset: Open Web Text

Neuron 1568 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: 4.4118. Min Range: -4.4118

Max Act: 4.4118. Min Act: -0.1700

Data Index: 2115995 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3592. Min Act: -0.1700

Data Index: 80690 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3572. Min Act: -0.1700

Data Index: 4530629 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3406. Min Act: -0.1700

Data Index: 3122137 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3486. Min Act: -0.1700

Data Index: 6821731 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3467. Min Act: -0.1700

Data Index: 837375 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3200. Min Act: -0.1700

Data Index: 1071221 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3203. Min Act: -0.1700

Data Index: 750954 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3137. Min Act: -0.1700

Data Index: 10557 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3221. Min Act: -0.1700

Data Index: 8750900 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.3101. Min Act: -0.1700

Data Index: 6701978 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2818. Min Act: -0.1700

Data Index: 1602608 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2890. Min Act: -0.1700

Data Index: 4085103 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2645. Min Act: -0.1700

Data Index: 3552477 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2942. Min Act: -0.1700

Data Index: 4559519 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2736. Min Act: -0.1700

Data Index: 4963865 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2710. Min Act: -0.1700

Data Index: 5697051 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2912. Min Act: -0.1700

Data Index: 5950290 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2939. Min Act: -0.1700

Data Index: 2015144 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.4118. Min Range: -4.4118

Max Act: 4.2691. Min Act: -0.1700

Data Index: 5993782 (Open Web Text)

Max Activating Token Index: 11