Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 985 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.4069. Min Act: -0.1700

Data Index: 85110 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3599. Min Act: -0.1700

Data Index: 875171 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3756. Min Act: -0.1700

Data Index: 1240701 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3442. Min Act: -0.1700

Data Index: 60740 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3128. Min Act: -0.1700

Data Index: 1264669 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3285. Min Act: -0.1700

Data Index: 999127 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3285. Min Act: -0.1700

Data Index: 452254 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2971. Min Act: -0.1700

Data Index: 512195 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2971. Min Act: -0.1700

Data Index: 1272417 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2657. Min Act: -0.1700

Data Index: 61123 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2971. Min Act: -0.1700

Data Index: 1185675 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.3128. Min Act: -0.1700

Data Index: 266499 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2971. Min Act: -0.1700

Data Index: 1329783 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2814. Min Act: -0.1700

Data Index: 193371 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2657. Min Act: -0.1700

Data Index: 246597 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1239628 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2971. Min Act: -0.1700

Data Index: 168681 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1190190 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2657. Min Act: -0.1700

Data Index: 803439 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.4069. Min Range: -3.4069

Max Act: 3.2657. Min Act: -0.1700

Data Index: 628187 (C4 (Web Text))

Max Activating Token Index: 872