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

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

Neuron 1033 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: 3.4225. Min Range: -3.4225

Max Act: 3.4225. Min Act: -0.1700

Data Index: 193 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.3912. Min Act: -0.1700

Data Index: 1374730 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.3284. Min Act: -0.1700

Data Index: 494468 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2813. Min Act: -0.1700

Data Index: 175420 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.3127. Min Act: -0.1700

Data Index: 1513516 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.3127. Min Act: -0.1700

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2027. Min Act: -0.1700

Data Index: 829249 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2656. Min Act: -0.1700

Data Index: 1329840 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2656. Min Act: -0.1700

Data Index: 277491 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2499. Min Act: -0.1700

Data Index: 937760 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2341. Min Act: -0.1700

Data Index: 834688 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2499. Min Act: -0.1700

Data Index: 800248 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2499. Min Act: -0.1700

Data Index: 236945 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.1869. Min Act: -0.1700

Data Index: 1235784 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2184. Min Act: -0.1700

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2027. Min Act: -0.1700

Data Index: 663808 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2027. Min Act: -0.1700

Data Index: 379505 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2027. Min Act: -0.1700

Data Index: 359589 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.2184. Min Act: -0.1700

Data Index: 1654760 (Python Code)

Max Activating Token Index: 638

Text #19

Max Range: 3.4225. Min Range: -3.4225

Max Act: 3.1869. Min Act: -0.1700

Data Index: 1400438 (Python Code)

Max Activating Token Index: 280