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

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

Neuron 884 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: 3.4738. Min Range: -3.4738

Max Act: 3.4738. Min Act: -0.1700

Data Index: 114892 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.4309. Min Act: -0.1700

Data Index: 930941 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.4034. Min Act: -0.1700

Data Index: 1006987 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3694. Min Act: -0.1700

Data Index: 1045923 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1297322 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.4011. Min Act: -0.1700

Data Index: 9053 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3495. Min Act: -0.1700

Data Index: 144932 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3738. Min Act: -0.1700

Data Index: 599445 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3371. Min Act: -0.1700

Data Index: 618689 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3438. Min Act: -0.1700

Data Index: 675033 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3229. Min Act: -0.1700

Data Index: 1539360 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3192. Min Act: -0.1700

Data Index: 1627586 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3185. Min Act: -0.1700

Data Index: 1008982 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3244. Min Act: -0.1700

Data Index: 1069938 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3322. Min Act: -0.1700

Data Index: 144567 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2957. Min Act: -0.1700

Data Index: 452585 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2861. Min Act: -0.1700

Data Index: 381777 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.3021. Min Act: -0.1700

Data Index: 149133 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2928. Min Act: -0.1700

Data Index: 803008 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 3.4738. Min Range: -3.4738

Max Act: 3.2799. Min Act: -0.1700

Data Index: 330152 (C4 (Web Text))

Max Activating Token Index: 480