Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 835 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.2226. Min Act: -0.1700

Data Index: 989750 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.2069. Min Act: -0.1700

Data Index: 1648335 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1754. Min Act: -0.1700

Data Index: 823788 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1597. Min Act: -0.1700

Data Index: 555532 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1439. Min Act: -0.1700

Data Index: 522745 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1124. Min Act: -0.1700

Data Index: 741061 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1047374 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1124. Min Act: -0.1700

Data Index: 260834 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1124. Min Act: -0.1700

Data Index: 1143678 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.1124. Min Act: -0.1700

Data Index: 145115 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0967. Min Act: -0.1700

Data Index: 375551 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0967. Min Act: -0.1700

Data Index: 367927 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 425318 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 273588 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 405306 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 835610 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 873540 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 376280 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 943669 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 3.2226. Min Range: -3.2226

Max Act: 3.0809. Min Act: -0.1700

Data Index: 431596 (C4 (Web Text))

Max Activating Token Index: 197