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

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

Neuron 1531 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.4071. Min Act: -0.1700

Data Index: 343887 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.3287. Min Act: -0.1700

Data Index: 1130304 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.3130. Min Act: -0.1700

Data Index: 1332282 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2973. Min Act: -0.1700

Data Index: 893136 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2973. Min Act: -0.1700

Data Index: 206365 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2816. Min Act: -0.1700

Data Index: 689441 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.3287. Min Act: -0.1700

Data Index: 569469 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2973. Min Act: -0.1700

Data Index: 79231 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1358547 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.3287. Min Act: -0.1700

Data Index: 559772 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2973. Min Act: -0.1700

Data Index: 496461 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2816. Min Act: -0.1700

Data Index: 1280037 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2658. Min Act: -0.1700

Data Index: 272763 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2658. Min Act: -0.1700

Data Index: 438235 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2501. Min Act: -0.1700

Data Index: 80076 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2501. Min Act: -0.1700

Data Index: 1290285 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2501. Min Act: -0.1700

Data Index: 528150 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2816. Min Act: -0.1700

Data Index: 139321 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2501. Min Act: -0.1700

Data Index: 265716 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 3.4071. Min Range: -3.4071

Max Act: 3.2501. Min Act: -0.1700

Data Index: 351659 (C4 (Web Text))

Max Activating Token Index: 960