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

Dataset: Open Web Text

Neuron 1183 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: 2.8419. Min Range: -2.8419

Max Act: 2.8372. Min Act: -0.1700

Data Index: 7226081 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.8419. Min Act: -0.1700

Data Index: 5698827 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.8004. Min Act: -0.1700

Data Index: 3455747 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7452. Min Act: -0.1700

Data Index: 3115310 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7539. Min Act: -0.1700

Data Index: 6230899 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7648. Min Act: -0.1700

Data Index: 747227 (Open Web Text)

Max Activating Token Index: 270

Text #6

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7547. Min Act: -0.1700

Data Index: 5982422 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7213. Min Act: -0.1700

Data Index: 3279260 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7241. Min Act: -0.1700

Data Index: 6682674 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7310. Min Act: -0.1700

Data Index: 4059169 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7192. Min Act: -0.1700

Data Index: 2466476 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7294. Min Act: -0.1700

Data Index: 5547249 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7275. Min Act: -0.1700

Data Index: 7265141 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7108. Min Act: -0.1700

Data Index: 5584029 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7098. Min Act: -0.1700

Data Index: 3991019 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7078. Min Act: -0.1700

Data Index: 5912367 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.6997. Min Act: -0.1700

Data Index: 5058732 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7063. Min Act: -0.1700

Data Index: 2684966 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7153. Min Act: -0.1700

Data Index: 3788253 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8419. Min Range: -2.8419

Max Act: 2.7100. Min Act: -0.1700

Data Index: 4633973 (Open Web Text)

Max Activating Token Index: 4