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

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

Neuron 947 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: 3.5147. Min Range: -3.5147

Max Act: 3.5147. Min Act: -0.1700

Data Index: 582589 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.4520. Min Act: -0.1700

Data Index: 904111 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.3736. Min Act: -0.1700

Data Index: 1329938 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.3265. Min Act: -0.1700

Data Index: 135403 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2794. Min Act: -0.1700

Data Index: 349547 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2794. Min Act: -0.1700

Data Index: 487740 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2951. Min Act: -0.1700

Data Index: 1004750 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2794. Min Act: -0.1700

Data Index: 70055 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2637. Min Act: -0.1700

Data Index: 807389 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2951. Min Act: -0.1700

Data Index: 910184 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2951. Min Act: -0.1700

Data Index: 381691 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2165. Min Act: -0.1700

Data Index: 1044002 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2951. Min Act: -0.1700

Data Index: 415964 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2637. Min Act: -0.1700

Data Index: 351853 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2951. Min Act: -0.1700

Data Index: 556457 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2794. Min Act: -0.1700

Data Index: 1052172 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2322. Min Act: -0.1700

Data Index: 795823 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2479. Min Act: -0.1700

Data Index: 724724 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2322. Min Act: -0.1700

Data Index: 1252114 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.5147. Min Range: -3.5147

Max Act: 3.2165. Min Act: -0.1700

Data Index: 104751 (C4 (Web Text))

Max Activating Token Index: 854