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

Dataset: Open Web Text

Neuron 2299 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: 5.0658. Min Range: -5.0658

Max Act: 5.0658. Min Act: -0.1700

Data Index: 6603801 (Open Web Text)

Max Activating Token Index: 649

Text #1

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.8067. Min Act: -0.1700

Data Index: 4187435 (Open Web Text)

Max Activating Token Index: 559

Text #2

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.8151. Min Act: -0.1700

Data Index: 7617148 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.8274. Min Act: -0.1700

Data Index: 6171154 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.8319. Min Act: -0.1700

Data Index: 2715392 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.8100. Min Act: -0.1700

Data Index: 7330077 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7878. Min Act: -0.1700

Data Index: 5846058 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7949. Min Act: -0.1700

Data Index: 8757497 (Open Web Text)

Max Activating Token Index: 96

Text #8

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7464. Min Act: -0.1700

Data Index: 8062064 (Open Web Text)

Max Activating Token Index: 806

Text #9

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7401. Min Act: -0.1700

Data Index: 7830600 (Open Web Text)

Max Activating Token Index: 921

Text #10

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7448. Min Act: -0.1700

Data Index: 3370726 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7769. Min Act: -0.1700

Data Index: 8130747 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7345. Min Act: -0.1700

Data Index: 6824660 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7266. Min Act: -0.1700

Data Index: 6851301 (Open Web Text)

Max Activating Token Index: 220

Text #14

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7158. Min Act: -0.1700

Data Index: 1224458 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7221. Min Act: -0.1700

Data Index: 2959595 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7167. Min Act: -0.1700

Data Index: 5659400 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7243. Min Act: -0.1700

Data Index: 5529161 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7412. Min Act: -0.1700

Data Index: 5331301 (Open Web Text)

Max Activating Token Index: 241

Text #19

Max Range: 5.0658. Min Range: -5.0658

Max Act: 4.7293. Min Act: -0.1700

Data Index: 1962213 (Open Web Text)

Max Activating Token Index: 805