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

Dataset: Open Web Text

Neuron 2050 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: 3.8169. Min Range: -3.8169

Max Act: 3.8169. Min Act: -0.1700

Data Index: 5360136 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.8085. Min Act: -0.1700

Data Index: 214471 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7840. Min Act: -0.1700

Data Index: 1001797 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7842. Min Act: -0.1700

Data Index: 2271744 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7878. Min Act: -0.1700

Data Index: 8457992 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7749. Min Act: -0.1700

Data Index: 3065312 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7409. Min Act: -0.1700

Data Index: 3911711 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7512. Min Act: -0.1700

Data Index: 7931541 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7545. Min Act: -0.1700

Data Index: 6448262 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7542. Min Act: -0.1700

Data Index: 2292278 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7080. Min Act: -0.1700

Data Index: 3027072 (Open Web Text)

Max Activating Token Index: 767

Text #11

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7348. Min Act: -0.1700

Data Index: 6347731 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7168. Min Act: -0.1700

Data Index: 6457662 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7229. Min Act: -0.1700

Data Index: 6856895 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7113. Min Act: -0.1700

Data Index: 2662959 (Open Web Text)

Max Activating Token Index: 671

Text #15

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7305. Min Act: -0.1700

Data Index: 8366651 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7293. Min Act: -0.1700

Data Index: 628111 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.6820. Min Act: -0.1700

Data Index: 3832886 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.7103. Min Act: -0.1700

Data Index: 1912059 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.6890. Min Act: -0.1700

Data Index: 1925508 (Open Web Text)

Max Activating Token Index: 33