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

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

Neuron 352 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: 3.4975. Min Range: -3.4975

Max Act: 3.4975. Min Act: -0.1700

Data Index: 250683 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3643. Min Act: -0.1422

Data Index: 872726 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3170. Min Act: -0.1682

Data Index: 359313 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3014. Min Act: -0.1699

Data Index: 1010768 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2902. Min Act: -0.1695

Data Index: 895719 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3078. Min Act: -0.1697

Data Index: 1023128 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1179908 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2762. Min Act: -0.1692

Data Index: 1275061 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2542. Min Act: -0.1699

Data Index: 583005 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2340. Min Act: -0.1696

Data Index: 476388 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2267. Min Act: -0.1700

Data Index: 199582 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2304. Min Act: -0.1700

Data Index: 970684 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2452. Min Act: -0.1700

Data Index: 47 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2194. Min Act: -0.1700

Data Index: 621163 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2335. Min Act: -0.1699

Data Index: 882205 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1962. Min Act: -0.1698

Data Index: 23798 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2024. Min Act: -0.1700

Data Index: 983192 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1964. Min Act: -0.1699

Data Index: 412503 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1178995 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.1967. Min Act: -0.1700

Data Index: 96944 (C4 (Web Text))

Max Activating Token Index: 539