Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 578 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0158. Min Range: -4.0158

Max Act: 4.0158. Min Act: -0.1700

Data Index: 1482439 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.9941. Min Act: -0.1700

Data Index: 1471602 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.9630. Min Act: -0.1700

Data Index: 1637340 (Python Code)

Max Activating Token Index: 339

Text #3

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.9293. Min Act: -0.1700

Data Index: 1375026 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8862. Min Act: -0.1700

Data Index: 992835 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8804. Min Act: -0.1700

Data Index: 1467394 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8454. Min Act: -0.1700

Data Index: 422852 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8557. Min Act: -0.1700

Data Index: 231004 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8542. Min Act: -0.1700

Data Index: 1441220 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8043. Min Act: -0.1700

Data Index: 1403250 (Python Code)

Max Activating Token Index: 543

Text #10

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8020. Min Act: -0.1700

Data Index: 1626917 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7882. Min Act: -0.1700

Data Index: 539062 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.8013. Min Act: -0.1700

Data Index: 379578 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7894. Min Act: -0.1700

Data Index: 1558329 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7781. Min Act: -0.1700

Data Index: 1102771 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7218. Min Act: -0.1700

Data Index: 1026046 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7539. Min Act: -0.1700

Data Index: 1409071 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1532784 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7462. Min Act: -0.1700

Data Index: 978591 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 4.0158. Min Range: -4.0158

Max Act: 3.7196. Min Act: -0.1700

Data Index: 698513 (C4 (Web Text))

Max Activating Token Index: 957