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

Dataset: Open Web Text

Neuron 2580 in Layer 2

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: 4.4210. Min Range: -4.4210

Max Act: 4.4210. Min Act: -0.1700

Data Index: 8001415 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.3243. Min Act: -0.1700

Data Index: 1046287 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.1924. Min Act: -0.1700

Data Index: 3489538 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.1745. Min Act: -0.1700

Data Index: 8444956 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.1750. Min Act: -0.1700

Data Index: 1795557 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.1648. Min Act: -0.1700

Data Index: 7660375 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.1127. Min Act: -0.1700

Data Index: 8241471 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0742. Min Act: -0.1700

Data Index: 4086186 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.1011. Min Act: -0.1700

Data Index: 4273460 (Open Web Text)

Max Activating Token Index: 991

Text #9

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0429. Min Act: -0.1700

Data Index: 7157306 (Open Web Text)

Max Activating Token Index: 73

Text #10

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0774. Min Act: -0.1700

Data Index: 6330609 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0704. Min Act: -0.1700

Data Index: 4046736 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0084. Min Act: -0.1700

Data Index: 6946333 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0135. Min Act: -0.1700

Data Index: 7575376 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0006. Min Act: -0.1700

Data Index: 7663446 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0023. Min Act: -0.1700

Data Index: 8246742 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 4.4210. Min Range: -4.4210

Max Act: 4.0141. Min Act: -0.1700

Data Index: 1485240 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 4.4210. Min Range: -4.4210

Max Act: 3.9883. Min Act: -0.1700

Data Index: 8535630 (Open Web Text)

Max Activating Token Index: 262

Text #18

Max Range: 4.4210. Min Range: -4.4210

Max Act: 3.9893. Min Act: -0.1700

Data Index: 4114922 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.4210. Min Range: -4.4210

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1672548 (Open Web Text)

Max Activating Token Index: 58