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

Dataset: Open Web Text

Neuron 18 in Layer 6

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: 5.5602. Min Range: -5.5602

Max Act: 5.5602. Min Act: -0.1700

Data Index: 6851787 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 5.5602. Min Range: -5.5602

Max Act: 5.1986. Min Act: -0.1700

Data Index: 2974745 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 5.5602. Min Range: -5.5602

Max Act: 5.1329. Min Act: -0.1700

Data Index: 5286501 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 5.5602. Min Range: -5.5602

Max Act: 5.1165. Min Act: -0.1700

Data Index: 5916006 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.5602. Min Range: -5.5602

Max Act: 5.0565. Min Act: -0.1700

Data Index: 578610 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 5.5602. Min Range: -5.5602

Max Act: 5.0562. Min Act: -0.1700

Data Index: 8429127 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 5.5602. Min Range: -5.5602

Max Act: 5.0213. Min Act: -0.1700

Data Index: 3452897 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.9904. Min Act: -0.1700

Data Index: 3398157 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.9871. Min Act: -0.1700

Data Index: 7524932 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.9216. Min Act: -0.1700

Data Index: 5776886 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.9570. Min Act: -0.1700

Data Index: 7104030 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.9457. Min Act: -0.1700

Data Index: 8145967 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8968. Min Act: -0.1700

Data Index: 3236098 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8934. Min Act: -0.1700

Data Index: 1447909 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8831. Min Act: -0.1700

Data Index: 5396928 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8103. Min Act: -0.1700

Data Index: 7547175 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8077. Min Act: -0.1700

Data Index: 3755015 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8170. Min Act: -0.1700

Data Index: 7531894 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8030. Min Act: -0.1700

Data Index: 8206798 (Open Web Text)

Max Activating Token Index: 58

Text #19

Max Range: 5.5602. Min Range: -5.5602

Max Act: 4.8205. Min Act: -0.1700

Data Index: 2766110 (Open Web Text)

Max Activating Token Index: 432