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

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

Neuron 83 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: 5.6512. Min Range: -5.6512

Max Act: 5.6512. Min Act: -0.1700

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.3699. Min Act: -0.1700

Data Index: 1250656 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.4012. Min Act: -0.1700

Data Index: 606553 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.4012. Min Act: -0.1700

Data Index: 850359 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2762. Min Act: -0.1700

Data Index: 140099 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.3387. Min Act: -0.1700

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2762. Min Act: -0.1700

Data Index: 592014 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2762. Min Act: -0.1700

Data Index: 117868 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2449. Min Act: -0.1700

Data Index: 981873 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2137. Min Act: -0.1700

Data Index: 227296 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2137. Min Act: -0.1700

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.3074. Min Act: -0.1700

Data Index: 375700 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2449. Min Act: -0.1700

Data Index: 568208 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2449. Min Act: -0.1700

Data Index: 141515 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.1512. Min Act: -0.1700

Data Index: 444872 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2449. Min Act: -0.1700

Data Index: 1119657 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2449. Min Act: -0.1700

Data Index: 994277 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.2449. Min Act: -0.1700

Data Index: 1279332 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.1824. Min Act: -0.1700

Data Index: 227994 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 5.6512. Min Range: -5.6512

Max Act: 5.1824. Min Act: -0.1700

Data Index: 241304 (C4 (Web Text))

Max Activating Token Index: 242