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

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

Neuron 860 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: 3.5491. Min Range: -3.5491

Max Act: 3.4864. Min Act: -0.1700

Data Index: 401459 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1602145 (Python Code)

Max Activating Token Index: 131

Text #2

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.4864. Min Act: -0.1700

Data Index: 412390 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.4237. Min Act: -0.1700

Data Index: 439555 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3923. Min Act: -0.1700

Data Index: 320 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.4237. Min Act: -0.1700

Data Index: 1167474 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3923. Min Act: -0.1700

Data Index: 811660 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 1488271 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 1551239 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 1625558 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 1525369 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3923. Min Act: -0.1700

Data Index: 434624 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3923. Min Act: -0.1700

Data Index: 924262 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 867456 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 803958 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3296. Min Act: -0.1700

Data Index: 799665 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3296. Min Act: -0.1700

Data Index: 1171362 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3296. Min Act: -0.1700

Data Index: 388279 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3610. Min Act: -0.1700

Data Index: 166307 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 3.5491. Min Range: -3.5491

Max Act: 3.3296. Min Act: -0.1700

Data Index: 1103324 (C4 (Web Text))

Max Activating Token Index: 84