Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1255 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5803. Min Act: -0.1700

Data Index: 971477 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5787. Min Act: -0.1700

Data Index: 796561 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5730. Min Act: -0.1700

Data Index: 1194457 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5578. Min Act: -0.1700

Data Index: 699895 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5628. Min Act: -0.1700

Data Index: 990493 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5267. Min Act: -0.1700

Data Index: 160213 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5091. Min Act: -0.1700

Data Index: 59517 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1317569 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4880. Min Act: -0.1700

Data Index: 486082 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4929. Min Act: -0.1700

Data Index: 880487 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5024. Min Act: -0.1700

Data Index: 618375 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5045. Min Act: -0.1700

Data Index: 350750 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.5026. Min Act: -0.1700

Data Index: 1154835 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4932. Min Act: -0.1700

Data Index: 424755 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4847. Min Act: -0.1700

Data Index: 1651438 (Python Code)

Max Activating Token Index: 87

Text #15

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4818. Min Act: -0.1700

Data Index: 26727 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4897. Min Act: -0.1700

Data Index: 461144 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4857. Min Act: -0.1700

Data Index: 287785 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4783. Min Act: -0.1700

Data Index: 762257 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 3.5803. Min Range: -3.5803

Max Act: 3.4771. Min Act: -0.1700

Data Index: 1040498 (C4 (Web Text))

Max Activating Token Index: 87