Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 469 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9817. Min Act: -0.1700

Data Index: 1634113 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8878. Min Act: -0.1700

Data Index: 1567945 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9191. Min Act: -0.1700

Data Index: 1483790 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9035. Min Act: -0.1700

Data Index: 1373054 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 4.0129. Min Range: -4.0129

Max Act: 4.0129. Min Act: -0.1700

Data Index: 1607524 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8409. Min Act: -0.1700

Data Index: 1388908 (Python Code)

Max Activating Token Index: 532

Text #6

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9191. Min Act: -0.1700

Data Index: 1623919 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8566. Min Act: -0.1700

Data Index: 1415596 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9035. Min Act: -0.1700

Data Index: 1590892 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8566. Min Act: -0.1700

Data Index: 1427753 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8566. Min Act: -0.1700

Data Index: 1604050 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8878. Min Act: -0.1700

Data Index: 1527822 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9347. Min Act: -0.1700

Data Index: 1375002 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9035. Min Act: -0.1700

Data Index: 1545044 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9347. Min Act: -0.1700

Data Index: 511612 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.9191. Min Act: -0.1700

Data Index: 1535024 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1595138 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8722. Min Act: -0.1700

Data Index: 1580714 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8722. Min Act: -0.1700

Data Index: 1585743 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 4.0129. Min Range: -4.0129

Max Act: 3.8566. Min Act: -0.1700

Data Index: 1617964 (Python Code)

Max Activating Token Index: 134