Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 634 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.2059. Min Act: -0.1700

Data Index: 624671 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.1429. Min Act: -0.1700

Data Index: 870231 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.1271. Min Act: -0.1700

Data Index: 27987 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.1114. Min Act: -0.1700

Data Index: 858834 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0956. Min Act: -0.1700

Data Index: 39583 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0641. Min Act: -0.1700

Data Index: 1280363 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0483. Min Act: -0.1700

Data Index: 860378 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0325. Min Act: -0.1700

Data Index: 1178761 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0325. Min Act: -0.1700

Data Index: 1098423 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0325. Min Act: -0.1700

Data Index: 1339680 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0009. Min Act: -0.1700

Data Index: 852355 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0009. Min Act: -0.1700

Data Index: 692923 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 3.2059. Min Range: -3.2059

Max Act: 3.0009. Min Act: -0.1700

Data Index: 35976 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9534. Min Act: -0.1700

Data Index: 951461 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9693. Min Act: -0.1700

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9534. Min Act: -0.1700

Data Index: 1266228 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9534. Min Act: -0.1700

Data Index: 514441 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9534. Min Act: -0.1700

Data Index: 1009990 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9376. Min Act: -0.1700

Data Index: 1052792 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 3.2059. Min Range: -3.2059

Max Act: 2.9534. Min Act: -0.1700

Data Index: 1100161 (C4 (Web Text))

Max Activating Token Index: 66