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

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

Neuron 532 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: 4.1943. Min Range: -4.1943

Max Act: 4.1943. Min Act: -0.1700

Data Index: 634070 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 4.1943. Min Range: -4.1943

Max Act: 4.1318. Min Act: -0.1700

Data Index: 136805 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.9442. Min Act: -0.1700

Data Index: 1340394 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.9755. Min Act: -0.1700

Data Index: 744818 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.9129. Min Act: -0.1700

Data Index: 1265443 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 159049 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.9442. Min Act: -0.1700

Data Index: 582074 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8504. Min Act: -0.1700

Data Index: 181000 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 170767 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8504. Min Act: -0.1700

Data Index: 781712 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 586275 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.7878. Min Act: -0.1700

Data Index: 49790 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8504. Min Act: -0.1700

Data Index: 318052 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.7878. Min Act: -0.1700

Data Index: 384816 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 148800 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 1007602 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 457401 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.7565. Min Act: -0.1700

Data Index: 10891 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.8191. Min Act: -0.1700

Data Index: 138846 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 4.1943. Min Range: -4.1943

Max Act: 3.7565. Min Act: -0.1700

Data Index: 914395 (C4 (Web Text))

Max Activating Token Index: 19