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

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

Neuron 739 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.4102. Min Act: -0.1700

Data Index: 74187 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.3003. Min Act: -0.1700

Data Index: 1198581 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2689. Min Act: -0.1700

Data Index: 783319 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2689. Min Act: -0.1700

Data Index: 1132731 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2689. Min Act: -0.1700

Data Index: 1113142 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1242592 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2689. Min Act: -0.1700

Data Index: 785537 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2375. Min Act: -0.1700

Data Index: 1407742 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2532. Min Act: -0.1700

Data Index: 380025 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2375. Min Act: -0.1700

Data Index: 947280 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2218. Min Act: -0.1700

Data Index: 656972 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1020747 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2218. Min Act: -0.1700

Data Index: 623155 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2218. Min Act: -0.1700

Data Index: 645973 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2060. Min Act: -0.1700

Data Index: 156281 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2218. Min Act: -0.1700

Data Index: 161697 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2375. Min Act: -0.1700

Data Index: 1289776 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.1903. Min Act: -0.1700

Data Index: 37171 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2218. Min Act: -0.1700

Data Index: 768468 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2218. Min Act: -0.1700

Data Index: 502593 (C4 (Web Text))

Max Activating Token Index: 987