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

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

Neuron 1415 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: 3.7673. Min Range: -3.7673

Max Act: 3.7673. Min Act: -0.1700

Data Index: 1412206 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6697. Min Act: -0.1700

Data Index: 1380174 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1614572 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6515. Min Act: -0.1700

Data Index: 1436660 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6485. Min Act: -0.1700

Data Index: 1509913 (Python Code)

Max Activating Token Index: 220

Text #5

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6386. Min Act: -0.1699

Data Index: 1607525 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1468408 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1548832 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.6075. Min Act: -0.1700

Data Index: 1623989 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5902. Min Act: -0.1700

Data Index: 1159771 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5569. Min Act: -0.1700

Data Index: 1050552 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5511. Min Act: -0.1700

Data Index: 1630043 (Python Code)

Max Activating Token Index: 829

Text #12

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5737. Min Act: -0.1700

Data Index: 1508162 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5510. Min Act: -0.1700

Data Index: 1447408 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5310. Min Act: -0.1700

Data Index: 1394931 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1422328 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.5132. Min Act: -0.1700

Data Index: 1405214 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.4831. Min Act: -0.1700

Data Index: 1485881 (Python Code)

Max Activating Token Index: 548

Text #18

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.4972. Min Act: -0.1700

Data Index: 1416617 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 3.7673. Min Range: -3.7673

Max Act: 3.4906. Min Act: -0.1700

Data Index: 1387681 (Python Code)

Max Activating Token Index: 542