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

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

Neuron 299 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: 3.6929. Min Range: -3.6929

Max Act: 3.6929. Min Act: -0.1700

Data Index: 1412845 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.5835. Min Act: -0.1700

Data Index: 1436751 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.5761. Min Act: -0.1700

Data Index: 1384357 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.5443. Min Act: -0.1699

Data Index: 1452645 (Python Code)

Max Activating Token Index: 856

Text #4

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4972. Min Act: -0.1700

Data Index: 461805 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4401. Min Act: -0.1700

Data Index: 1071283 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4488. Min Act: -0.1697

Data Index: 1614009 (Python Code)

Max Activating Token Index: 181

Text #7

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4372. Min Act: -0.1699

Data Index: 1628393 (Python Code)

Max Activating Token Index: 789

Text #8

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4444. Min Act: -0.1699

Data Index: 1433189 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4378. Min Act: -0.1700

Data Index: 1408141 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4249. Min Act: -0.1700

Data Index: 1569405 (Python Code)

Max Activating Token Index: 753

Text #11

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4410. Min Act: -0.1700

Data Index: 912536 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4360. Min Act: -0.1700

Data Index: 548570 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4098. Min Act: -0.1700

Data Index: 1425036 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4151. Min Act: -0.1700

Data Index: 714711 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4178. Min Act: -0.1699

Data Index: 319933 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4156. Min Act: -0.1700

Data Index: 1457812 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4034. Min Act: -0.1700

Data Index: 1529026 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.3961. Min Act: -0.1697

Data Index: 1516166 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 3.6929. Min Range: -3.6929

Max Act: 3.4011. Min Act: -0.1700

Data Index: 59751 (C4 (Web Text))

Max Activating Token Index: 608