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

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

Neuron 1746 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: 3.5946. Min Range: -3.5946

Max Act: 3.5946. Min Act: -0.1700

Data Index: 1454440 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4667. Min Act: -0.1700

Data Index: 1591803 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4838. Min Act: -0.1700

Data Index: 1587502 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4422. Min Act: -0.1700

Data Index: 1368195 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4040. Min Act: -0.1700

Data Index: 1541501 (Python Code)

Max Activating Token Index: 600

Text #5

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3957. Min Act: -0.1700

Data Index: 1425594 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3943. Min Act: -0.1700

Data Index: 1476827 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3903. Min Act: -0.1700

Data Index: 1623330 (Python Code)

Max Activating Token Index: 471

Text #8

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3415. Min Act: -0.1700

Data Index: 829685 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3356. Min Act: -0.1700

Data Index: 1565155 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3342. Min Act: -0.1699

Data Index: 1456335 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3202. Min Act: -0.1699

Data Index: 1460920 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3242. Min Act: -0.1700

Data Index: 1458065 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.2698. Min Act: -0.1698

Data Index: 1445698 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.2955. Min Act: -0.1700

Data Index: 1458959 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.2916. Min Act: -0.1700

Data Index: 1472029 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.2777. Min Act: -0.1700

Data Index: 1403125 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3036. Min Act: -0.1700

Data Index: 1426153 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1480243 (Python Code)

Max Activating Token Index: 454

Text #19

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.2437. Min Act: -0.1700

Data Index: 1515594 (Python Code)

Max Activating Token Index: 736