Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1197 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.2129. Min Act: -0.1700

Data Index: 21014 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.1816. Min Act: -0.1700

Data Index: 967570 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.1504. Min Act: -0.1700

Data Index: 1249364 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.1191. Min Act: -0.1700

Data Index: 27999 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0879. Min Act: -0.1700

Data Index: 324334 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0566. Min Act: -0.1700

Data Index: 1078033 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0566. Min Act: -0.1700

Data Index: 400122 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0879. Min Act: -0.1700

Data Index: 542950 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9941. Min Act: -0.1700

Data Index: 1525673 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0254. Min Act: -0.1700

Data Index: 963669 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0566. Min Act: -0.1700

Data Index: 266132 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9941. Min Act: -0.1700

Data Index: 981027 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9629. Min Act: -0.1700

Data Index: 360117 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 5.2129. Min Range: -5.2129

Max Act: 5.0254. Min Act: -0.1700

Data Index: 528382 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9941. Min Act: -0.1700

Data Index: 1176471 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9629. Min Act: -0.1700

Data Index: 562843 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9629. Min Act: -0.1700

Data Index: 1183091 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9629. Min Act: -0.1700

Data Index: 1011110 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9629. Min Act: -0.1700

Data Index: 801561 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 5.2129. Min Range: -5.2129

Max Act: 4.9941. Min Act: -0.1700

Data Index: 529549 (C4 (Web Text))

Max Activating Token Index: 296