Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 777 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.4610. Min Act: -0.1700

Data Index: 91204 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.3047. Min Act: -0.1700

Data Index: 516766 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.3360. Min Act: -0.1700

Data Index: 169672 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2110. Min Act: -0.1700

Data Index: 1209335 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2735. Min Act: -0.1700

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2422. Min Act: -0.1700

Data Index: 358206 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1797. Min Act: -0.1700

Data Index: 547532 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2110. Min Act: -0.1700

Data Index: 741948 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2110. Min Act: -0.1700

Data Index: 347108 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1797. Min Act: -0.1700

Data Index: 1353724 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2110. Min Act: -0.1700

Data Index: 739279 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2422. Min Act: -0.1700

Data Index: 100744 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2110. Min Act: -0.1700

Data Index: 460352 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2422. Min Act: -0.1700

Data Index: 903495 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1797. Min Act: -0.1700

Data Index: 48971 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1172. Min Act: -0.1700

Data Index: 283966 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2110. Min Act: -0.1700

Data Index: 732638 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1797. Min Act: -0.1700

Data Index: 834871 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1485. Min Act: -0.1700

Data Index: 780528 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.1485. Min Act: -0.1700

Data Index: 688878 (C4 (Web Text))

Max Activating Token Index: 786