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

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

Neuron 1153 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: 5.0962. Min Range: -5.0962

Max Act: 5.0962. Min Act: -0.1700

Data Index: 633518 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.8462. Min Act: -0.1700

Data Index: 989169 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.8150. Min Act: -0.1700

Data Index: 120477 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.8150. Min Act: -0.1700

Data Index: 315310 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.7525. Min Act: -0.1700

Data Index: 1064089 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.7212. Min Act: -0.1700

Data Index: 1267571 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.7212. Min Act: -0.1700

Data Index: 81589 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.6587. Min Act: -0.1700

Data Index: 1180325 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.6587. Min Act: -0.1700

Data Index: 458900 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5337. Min Act: -0.1700

Data Index: 339563 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5962. Min Act: -0.1700

Data Index: 1233071 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5962. Min Act: -0.1700

Data Index: 1077594 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5650. Min Act: -0.1700

Data Index: 152813 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5650. Min Act: -0.1700

Data Index: 82286 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5650. Min Act: -0.1700

Data Index: 456858 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5650. Min Act: -0.1700

Data Index: 877362 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5962. Min Act: -0.1700

Data Index: 712443 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5650. Min Act: -0.1700

Data Index: 1222652 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5962. Min Act: -0.1700

Data Index: 20692 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 5.0962. Min Range: -5.0962

Max Act: 4.5650. Min Act: -0.1700

Data Index: 768681 (C4 (Web Text))

Max Activating Token Index: 242