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

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

Neuron 214 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: 4.7953. Min Range: -4.7953

Max Act: 4.7953. Min Act: -0.1700

Data Index: 660570 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.6912. Min Act: -0.1700

Data Index: 1041673 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.6194. Min Act: -0.1700

Data Index: 1264267 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.5213. Min Act: -0.1700

Data Index: 358862 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.5574. Min Act: -0.1700

Data Index: 444334 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4993. Min Act: -0.1700

Data Index: 1224474 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4699. Min Act: -0.1700

Data Index: 1324207 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4726. Min Act: -0.1700

Data Index: 373830 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4477. Min Act: -0.1700

Data Index: 1495785 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4494. Min Act: -0.1700

Data Index: 1007553 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4036. Min Act: -0.1700

Data Index: 1197342 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4224. Min Act: -0.1700

Data Index: 615728 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3922. Min Act: -0.1700

Data Index: 69051 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3802. Min Act: -0.1700

Data Index: 425936 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3654. Min Act: -0.1700

Data Index: 496868 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3847. Min Act: -0.1700

Data Index: 269548 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3468. Min Act: -0.1700

Data Index: 440265 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3400. Min Act: -0.1700

Data Index: 137281 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3503. Min Act: -0.1700

Data Index: 1162686 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.3489. Min Act: -0.1700

Data Index: 72284 (C4 (Web Text))

Max Activating Token Index: 151