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

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

Neuron 1242 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: 7.5213. Min Range: -7.5213

Max Act: 7.5213. Min Act: -0.1700

Data Index: 439681 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.5213. Min Act: -0.1700

Data Index: 1321708 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.4588. Min Act: -0.1700

Data Index: 1349306 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.3338. Min Act: -0.1700

Data Index: 586152 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.3338. Min Act: -0.1700

Data Index: 212636 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.3338. Min Act: -0.1700

Data Index: 634600 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.3338. Min Act: -0.1700

Data Index: 357944 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.1463. Min Act: -0.1700

Data Index: 132248 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2088. Min Act: -0.1700

Data Index: 266401 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2713. Min Act: -0.1700

Data Index: 296913 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2088. Min Act: -0.1700

Data Index: 613031 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2088. Min Act: -0.1700

Data Index: 258148 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2713. Min Act: -0.1700

Data Index: 834945 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2713. Min Act: -0.1700

Data Index: 431054 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2088. Min Act: -0.1700

Data Index: 1298533 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.0838. Min Act: -0.1700

Data Index: 717808 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2088. Min Act: -0.1700

Data Index: 629015 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.1463. Min Act: -0.1700

Data Index: 833934 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.2088. Min Act: -0.1700

Data Index: 322570 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 7.5213. Min Range: -7.5213

Max Act: 7.1463. Min Act: -0.1700

Data Index: 558438 (C4 (Web Text))

Max Activating Token Index: 155