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

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

Neuron 1547 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: 3.7237. Min Range: -3.7237

Max Act: 3.7237. Min Act: -0.1700

Data Index: 1173581 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.6823. Min Act: -0.1700

Data Index: 1448270 (Python Code)

Max Activating Token Index: 293

Text #2

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.6009. Min Act: -0.1700

Data Index: 897777 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.4866. Min Act: -0.1700

Data Index: 184626 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.4414. Min Act: -0.1700

Data Index: 873901 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.4061. Min Act: -0.1700

Data Index: 385592 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.4017. Min Act: -0.1699

Data Index: 77156 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3660. Min Act: -0.1700

Data Index: 1054302 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3713. Min Act: -0.1700

Data Index: 851215 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3659. Min Act: -0.1700

Data Index: 1597768 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3497. Min Act: -0.1700

Data Index: 1465019 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3494. Min Act: -0.1699

Data Index: 1477991 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3496. Min Act: -0.1700

Data Index: 1192683 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3440. Min Act: -0.1700

Data Index: 1330176 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3500. Min Act: -0.1700

Data Index: 263778 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3276. Min Act: -0.1700

Data Index: 1156286 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3249. Min Act: -0.1700

Data Index: 246826 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3310. Min Act: -0.1700

Data Index: 82799 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3410. Min Act: -0.1700

Data Index: 178965 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 3.7237. Min Range: -3.7237

Max Act: 3.3309. Min Act: -0.1700

Data Index: 1420804 (Python Code)

Max Activating Token Index: 1005