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

Dataset: Open Web Text

Neuron 1010 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: 2.0031. Min Range: -2.0031

Max Act: 2.0031. Min Act: -0.1700

Data Index: 6741042 (Open Web Text)

Max Activating Token Index: 136

Text #1

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.9922. Min Act: -0.1700

Data Index: 970321 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.9018. Min Act: -0.1700

Data Index: 8693969 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8806. Min Act: -0.1700

Data Index: 5818021 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8677. Min Act: -0.1700

Data Index: 4689740 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8714. Min Act: -0.1700

Data Index: 1689385 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8553. Min Act: -0.1700

Data Index: 2131769 (Open Web Text)

Max Activating Token Index: 565

Text #7

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8626. Min Act: -0.1700

Data Index: 7807177 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8316. Min Act: -0.1700

Data Index: 7744604 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8403. Min Act: -0.1700

Data Index: 8491383 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8554. Min Act: -0.1700

Data Index: 402422 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8464. Min Act: -0.1700

Data Index: 4799643 (Open Web Text)

Max Activating Token Index: 154

Text #12

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8271. Min Act: -0.1700

Data Index: 171092 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8383. Min Act: -0.1700

Data Index: 4123440 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8444. Min Act: -0.1700

Data Index: 7273949 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8335. Min Act: -0.1700

Data Index: 6292966 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8363. Min Act: -0.1700

Data Index: 8109760 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8251. Min Act: -0.1700

Data Index: 1726247 (Open Web Text)

Max Activating Token Index: 529

Text #18

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8349. Min Act: -0.1700

Data Index: 6583172 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.0031. Min Range: -2.0031

Max Act: 1.8331. Min Act: -0.1700

Data Index: 7415447 (Open Web Text)

Max Activating Token Index: 950