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

Dataset: Open Web Text

Neuron 2620 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: 4.1325. Min Range: -4.1325

Max Act: 4.1325. Min Act: -0.1700

Data Index: 2070323 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 4.1325. Min Range: -4.1325

Max Act: 4.0408. Min Act: -0.1700

Data Index: 1369532 (Open Web Text)

Max Activating Token Index: 1018

Text #2

Max Range: 4.1325. Min Range: -4.1325

Max Act: 4.0346. Min Act: -0.1700

Data Index: 7852530 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 4.1325. Min Range: -4.1325

Max Act: 4.0252. Min Act: -0.1700

Data Index: 1547251 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 4.1325. Min Range: -4.1325

Max Act: 4.0095. Min Act: -0.1700

Data Index: 6656780 (Open Web Text)

Max Activating Token Index: 698

Text #5

Max Range: 4.1325. Min Range: -4.1325

Max Act: 4.0100. Min Act: -0.1700

Data Index: 3169579 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9948. Min Act: -0.1700

Data Index: 551704 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9879. Min Act: -0.1700

Data Index: 3634128 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9834. Min Act: -0.1700

Data Index: 1199112 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9726. Min Act: -0.1700

Data Index: 5903985 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9755. Min Act: -0.1700

Data Index: 4910675 (Open Web Text)

Max Activating Token Index: 746

Text #11

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9953. Min Act: -0.1700

Data Index: 721182 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9899. Min Act: -0.1700

Data Index: 8687875 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9685. Min Act: -0.1700

Data Index: 8457348 (Open Web Text)

Max Activating Token Index: 73

Text #14

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9776. Min Act: -0.1700

Data Index: 7475888 (Open Web Text)

Max Activating Token Index: 303

Text #15

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9661. Min Act: -0.1700

Data Index: 8349892 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9538. Min Act: -0.1700

Data Index: 2371605 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9865. Min Act: -0.1700

Data Index: 246459 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9866. Min Act: -0.1700

Data Index: 1523627 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 4.1325. Min Range: -4.1325

Max Act: 3.9420. Min Act: -0.1700

Data Index: 342430 (Open Web Text)

Max Activating Token Index: 185