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

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

Neuron 761 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: 3.3441. Min Range: -3.3441

Max Act: 3.3327. Min Act: -0.1700

Data Index: 459288 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.3404. Min Act: -0.1700

Data Index: 431060 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.3441. Min Act: -0.1700

Data Index: 649481 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.3325. Min Act: -0.1700

Data Index: 837514 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.3023. Min Act: -0.1700

Data Index: 1107279 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2956. Min Act: -0.1700

Data Index: 702497 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2654. Min Act: -0.1700

Data Index: 218098 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2625. Min Act: -0.1700

Data Index: 1280097 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2536. Min Act: -0.1700

Data Index: 219983 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2029. Min Act: -0.1700

Data Index: 1146262 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2817. Min Act: -0.1700

Data Index: 1158339 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2681. Min Act: -0.1700

Data Index: 720914 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2335. Min Act: -0.1700

Data Index: 914379 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2281. Min Act: -0.1700

Data Index: 975203 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2409. Min Act: -0.1700

Data Index: 644865 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2276. Min Act: -0.1700

Data Index: 1232214 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2381. Min Act: -0.1700

Data Index: 140558 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2001. Min Act: -0.1700

Data Index: 1069544 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.1964. Min Act: -0.1700

Data Index: 681048 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.3441. Min Range: -3.3441

Max Act: 3.2039. Min Act: -0.1700

Data Index: 837916 (C4 (Web Text))

Max Activating Token Index: 582