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

Dataset: Open Web Text

Neuron 568 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: 1.8951. Min Range: -1.8951

Max Act: 1.8951. Min Act: -0.1700

Data Index: 4592771 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8938. Min Act: -0.1700

Data Index: 4165590 (Open Web Text)

Max Activating Token Index: 62

Text #2

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8725. Min Act: -0.1700

Data Index: 5062131 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8777. Min Act: -0.1699

Data Index: 46581 (Open Web Text)

Max Activating Token Index: 94

Text #4

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8399. Min Act: -0.1700

Data Index: 3841152 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8319. Min Act: -0.1700

Data Index: 4734843 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8368. Min Act: -0.1700

Data Index: 6941438 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8408. Min Act: -0.1700

Data Index: 5673934 (Open Web Text)

Max Activating Token Index: 489

Text #8

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8153. Min Act: -0.1700

Data Index: 7418025 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8202. Min Act: -0.1699

Data Index: 546844 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8220. Min Act: -0.1700

Data Index: 6994807 (Open Web Text)

Max Activating Token Index: 59

Text #11

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8113. Min Act: -0.1700

Data Index: 7557853 (Open Web Text)

Max Activating Token Index: 748

Text #12

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8097. Min Act: -0.1700

Data Index: 3544641 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8144. Min Act: -0.1700

Data Index: 976617 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.7916. Min Act: -0.1700

Data Index: 3231134 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8119. Min Act: -0.1700

Data Index: 3183687 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8040. Min Act: -0.1700

Data Index: 3021904 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.7949. Min Act: -0.1700

Data Index: 4262897 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8037. Min Act: -0.1700

Data Index: 528262 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 1.8951. Min Range: -1.8951

Max Act: 1.8019. Min Act: -0.1700

Data Index: 5146908 (Open Web Text)

Max Activating Token Index: 506