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

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

Neuron 1409 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: 3.9494. Min Range: -3.9494

Max Act: 3.9494. Min Act: -0.1700

Data Index: 122401 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8188. Min Act: -0.1700

Data Index: 33930 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8066. Min Act: -0.1699

Data Index: 59609 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.8104. Min Act: -0.1698

Data Index: 353716 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7636. Min Act: -0.1700

Data Index: 981976 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7520. Min Act: -0.1699

Data Index: 1301671 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7185. Min Act: -0.1700

Data Index: 1177160 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7136. Min Act: -0.1699

Data Index: 328827 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7060. Min Act: -0.1699

Data Index: 383209 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7101. Min Act: -0.1700

Data Index: 1211188 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7044. Min Act: -0.1700

Data Index: 1225389 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.7041. Min Act: -0.1699

Data Index: 478169 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6861. Min Act: -0.1700

Data Index: 1260767 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6921. Min Act: -0.1700

Data Index: 689078 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6833. Min Act: -0.1700

Data Index: 418027 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6695. Min Act: -0.1699

Data Index: 785633 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6780. Min Act: -0.1700

Data Index: 615457 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6551. Min Act: -0.1700

Data Index: 796520 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6618. Min Act: -0.1700

Data Index: 889485 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 3.9494. Min Range: -3.9494

Max Act: 3.6415. Min Act: -0.1700

Data Index: 742856 (C4 (Web Text))

Max Activating Token Index: 581