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

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

Neuron 1103 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.7705. Min Act: -0.1700

Data Index: 845548 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.7705. Min Act: -0.1700

Data Index: 852228 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1158912 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6766. Min Act: -0.1700

Data Index: 109394 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.7079. Min Act: -0.1700

Data Index: 1241593 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1318280 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6140. Min Act: -0.1700

Data Index: 1081375 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6453. Min Act: -0.1700

Data Index: 224121 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6296. Min Act: -0.1700

Data Index: 244845 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6140. Min Act: -0.1700

Data Index: 1062854 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6296. Min Act: -0.1700

Data Index: 1120207 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6609. Min Act: -0.1700

Data Index: 174286 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6296. Min Act: -0.1700

Data Index: 841412 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.6296. Min Act: -0.1700

Data Index: 906211 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5983. Min Act: -0.1700

Data Index: 948585 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5983. Min Act: -0.1700

Data Index: 635539 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5670. Min Act: -0.1700

Data Index: 239342 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5670. Min Act: -0.1700

Data Index: 155163 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5983. Min Act: -0.1700

Data Index: 846602 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 3.7705. Min Range: -3.7705

Max Act: 3.5200. Min Act: -0.1700

Data Index: 90244 (C4 (Web Text))

Max Activating Token Index: 82