Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 921 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.7241. Min Act: -0.1700

Data Index: 924813 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.6303. Min Act: -0.1700

Data Index: 839311 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.6303. Min Act: -0.1700

Data Index: 690801 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.5366. Min Act: -0.1700

Data Index: 466949 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.2241. Min Act: -0.1700

Data Index: 255663 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.0366. Min Act: -0.1700

Data Index: 434934 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.0053. Min Act: -0.1700

Data Index: 506593 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 5.7241. Min Range: -5.7241

Max Act: 5.0053. Min Act: -0.1700

Data Index: 42814 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.9116. Min Act: -0.1700

Data Index: 1213140 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.8803. Min Act: -0.1700

Data Index: 92845 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.9428. Min Act: -0.1700

Data Index: 111939 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.8491. Min Act: -0.1700

Data Index: 1347756 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.8803. Min Act: -0.1700

Data Index: 657226 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.7553. Min Act: -0.1700

Data Index: 415224 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.8178. Min Act: -0.1700

Data Index: 262352 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.7553. Min Act: -0.1700

Data Index: 539292 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.7553. Min Act: -0.1700

Data Index: 529956 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.7866. Min Act: -0.1700

Data Index: 796827 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.7241. Min Act: -0.1700

Data Index: 631278 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 5.7241. Min Range: -5.7241

Max Act: 4.7241. Min Act: -0.1700

Data Index: 799278 (C4 (Web Text))

Max Activating Token Index: 212