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

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

Neuron 1122 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8942. Min Act: -0.1700

Data Index: 867696 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7378. Min Act: -0.1700

Data Index: 52142 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6752. Min Act: -0.1700

Data Index: 133705 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1050086 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1203333 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6595. Min Act: -0.1700

Data Index: 1129648 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6126. Min Act: -0.1700

Data Index: 336305 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1094981 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6439. Min Act: -0.1700

Data Index: 948830 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1310579 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5969. Min Act: -0.1700

Data Index: 378825 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5969. Min Act: -0.1700

Data Index: 969395 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5813. Min Act: -0.1700

Data Index: 261811 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5969. Min Act: -0.1700

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5969. Min Act: -0.1700

Data Index: 734592 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1060670 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5813. Min Act: -0.1700

Data Index: 1013090 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5969. Min Act: -0.1700

Data Index: 904646 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1098755 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.5499. Min Act: -0.1700

Data Index: 87509 (C4 (Web Text))

Max Activating Token Index: 646