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

Dataset: Open Web Text

Neuron 878 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: 3.8968. Min Range: -3.8968

Max Act: 3.8968. Min Act: -0.1700

Data Index: 663968 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8405. Min Act: -0.1700

Data Index: 4987407 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8532. Min Act: -0.1700

Data Index: 3400978 (Open Web Text)

Max Activating Token Index: 618

Text #3

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8511. Min Act: -0.1700

Data Index: 7729931 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8600. Min Act: -0.1700

Data Index: 5366794 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8596. Min Act: -0.1700

Data Index: 236477 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8258. Min Act: -0.1700

Data Index: 2522197 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1059421 (Open Web Text)

Max Activating Token Index: 235

Text #8

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8276. Min Act: -0.1700

Data Index: 7308290 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8397. Min Act: -0.1700

Data Index: 4251452 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8161. Min Act: -0.1700

Data Index: 7016962 (Open Web Text)

Max Activating Token Index: 598

Text #11

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7996. Min Act: -0.1700

Data Index: 2559128 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1656904 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8017. Min Act: -0.1700

Data Index: 671640 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8217. Min Act: -0.1700

Data Index: 7903431 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.8198. Min Act: -0.1700

Data Index: 2243988 (Open Web Text)

Max Activating Token Index: 877

Text #16

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7530. Min Act: -0.1700

Data Index: 107607 (Open Web Text)

Max Activating Token Index: 711

Text #17

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7552. Min Act: -0.1700

Data Index: 2751256 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7594. Min Act: -0.1700

Data Index: 3057432 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 3.8968. Min Range: -3.8968

Max Act: 3.7698. Min Act: -0.1700

Data Index: 3070903 (Open Web Text)

Max Activating Token Index: 918