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

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

Neuron 1650 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: 3.7586. Min Range: -3.7586

Max Act: 3.7586. Min Act: -0.1700

Data Index: 607671 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.7421. Min Act: -0.1700

Data Index: 388019 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6951. Min Act: -0.1652

Data Index: 344260 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6840. Min Act: -0.1700

Data Index: 1271748 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6645. Min Act: -0.1700

Data Index: 481942 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6492. Min Act: -0.1700

Data Index: 709798 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6475. Min Act: -0.1700

Data Index: 466889 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6867. Min Act: -0.1700

Data Index: 43247 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6431. Min Act: -0.1700

Data Index: 341332 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.6240. Min Act: -0.1700

Data Index: 192498 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5824. Min Act: -0.1700

Data Index: 1147810 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5847. Min Act: -0.1700

Data Index: 298660 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5915. Min Act: -0.1700

Data Index: 717020 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5758. Min Act: -0.1700

Data Index: 599906 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5911. Min Act: -0.1699

Data Index: 502659 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5762. Min Act: -0.1700

Data Index: 1359500 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5470. Min Act: -0.1699

Data Index: 969488 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5436. Min Act: -0.1700

Data Index: 177622 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5243. Min Act: -0.1700

Data Index: 862156 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.7586. Min Range: -3.7586

Max Act: 3.5307. Min Act: -0.1700

Data Index: 345448 (C4 (Web Text))

Max Activating Token Index: 428