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

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

Neuron 1313 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.5028. Min Act: -0.1700

Data Index: 122012 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.2203. Min Act: -0.1700

Data Index: 998926 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.2360. Min Act: -0.1700

Data Index: 1256700 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.1416. Min Act: -0.1700

Data Index: 1134581 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.1416. Min Act: -0.1700

Data Index: 170689 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0785. Min Act: -0.1700

Data Index: 285358 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1271412 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0627. Min Act: -0.1700

Data Index: 1319271 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1351053 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1047337 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0312. Min Act: -0.1700

Data Index: 96808 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.1100. Min Act: -0.1700

Data Index: 862657 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0785. Min Act: -0.1700

Data Index: 561866 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0312. Min Act: -0.1700

Data Index: 986549 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0312. Min Act: -0.1700

Data Index: 1000963 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0312. Min Act: -0.1700

Data Index: 225617 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1196739 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.5028. Min Range: -3.5028

Max Act: 2.9521. Min Act: -0.1700

Data Index: 529066 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0312. Min Act: -0.1700

Data Index: 992246 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 3.5028. Min Range: -3.5028

Max Act: 3.0469. Min Act: -0.1700

Data Index: 489707 (C4 (Web Text))

Max Activating Token Index: 371