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

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

Neuron 1717 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1288575 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1498230 (Python Code)

Max Activating Token Index: 580

Text #2

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.1273. Min Act: -0.1700

Data Index: 580121 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0958. Min Act: -0.1700

Data Index: 226230 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0800. Min Act: -0.1700

Data Index: 1264079 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0643. Min Act: -0.1700

Data Index: 10628 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0800. Min Act: -0.1700

Data Index: 1007905 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0485. Min Act: -0.1700

Data Index: 1165050 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0485. Min Act: -0.1700

Data Index: 929332 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0169. Min Act: -0.1700

Data Index: 1598375 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0169. Min Act: -0.1700

Data Index: 870386 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1106168 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0327. Min Act: -0.1700

Data Index: 228410 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0327. Min Act: -0.1700

Data Index: 93658 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0169. Min Act: -0.1700

Data Index: 984518 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1215832 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0011. Min Act: -0.1700

Data Index: 1269405 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0011. Min Act: -0.1700

Data Index: 155021 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 3.1431. Min Range: -3.1431

Max Act: 3.0011. Min Act: -0.1700

Data Index: 892863 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 3.1431. Min Range: -3.1431

Max Act: 2.9853. Min Act: -0.1700

Data Index: 1043073 (C4 (Web Text))

Max Activating Token Index: 678