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

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

Neuron 733 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: 3.5061. Min Range: -3.5061

Max Act: 3.5061. Min Act: -0.1700

Data Index: 495166 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.4822. Min Act: -0.1700

Data Index: 1145377 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3948. Min Act: -0.1700

Data Index: 477455 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1086241 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.4270. Min Act: -0.1700

Data Index: 779702 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3973. Min Act: -0.1700

Data Index: 620378 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3868. Min Act: -0.1700

Data Index: 197879 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.4073. Min Act: -0.1700

Data Index: 981394 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3798. Min Act: -0.1700

Data Index: 1345817 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3479. Min Act: -0.1700

Data Index: 935184 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3202. Min Act: -0.1700

Data Index: 214321 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3541. Min Act: -0.1700

Data Index: 605724 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3307. Min Act: -0.1700

Data Index: 748115 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3193. Min Act: -0.1700

Data Index: 453151 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3021. Min Act: -0.1700

Data Index: 1072934 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3275. Min Act: -0.1700

Data Index: 574775 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.3297. Min Act: -0.1700

Data Index: 1082985 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.2825. Min Act: -0.1700

Data Index: 111577 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.2927. Min Act: -0.1700

Data Index: 1182107 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 3.5061. Min Range: -3.5061

Max Act: 3.2480. Min Act: -0.1700

Data Index: 1416677 (Python Code)

Max Activating Token Index: 917