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

Dataset: Open Web Text

Neuron 2523 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: 1.8507. Min Range: -1.8507

Max Act: 1.8507. Min Act: -0.1700

Data Index: 6922907 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8338. Min Act: -0.1700

Data Index: 3042396 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8356. Min Act: -0.1700

Data Index: 6941590 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8105. Min Act: -0.1700

Data Index: 8761570 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8158. Min Act: -0.1700

Data Index: 1890860 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8120. Min Act: -0.1700

Data Index: 6966276 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7937. Min Act: -0.1700

Data Index: 1036304 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8043. Min Act: -0.1700

Data Index: 7533893 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8022. Min Act: -0.1700

Data Index: 2403225 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8113. Min Act: -0.1700

Data Index: 1048330 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8127. Min Act: -0.1700

Data Index: 3256130 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7894. Min Act: -0.1700

Data Index: 6692897 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7790. Min Act: -0.1700

Data Index: 5776941 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7735. Min Act: -0.1700

Data Index: 2156431 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7832. Min Act: -0.1700

Data Index: 3794045 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7829. Min Act: -0.1700

Data Index: 6735196 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7980. Min Act: -0.1700

Data Index: 4473037 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7941. Min Act: -0.1700

Data Index: 3544912 (Open Web Text)

Max Activating Token Index: 493

Text #18

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7958. Min Act: -0.1700

Data Index: 7713785 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.7829. Min Act: -0.1700

Data Index: 1272406 (Open Web Text)

Max Activating Token Index: 41