Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1347 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.5261. Min Act: -0.1700

Data Index: 271240 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.5212. Min Act: -0.1700

Data Index: 653441 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3774. Min Act: -0.1700

Data Index: 248307 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3667. Min Act: -0.1700

Data Index: 491188 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3429. Min Act: -0.1700

Data Index: 506540 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3430. Min Act: -0.1700

Data Index: 367812 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3146. Min Act: -0.1700

Data Index: 514044 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3256. Min Act: -0.1700

Data Index: 1158068 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3061. Min Act: -0.1700

Data Index: 28051 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3043. Min Act: -0.1700

Data Index: 689186 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2888. Min Act: -0.1700

Data Index: 1177006 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2862. Min Act: -0.1700

Data Index: 719272 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2766. Min Act: -0.1700

Data Index: 194235 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2731. Min Act: -0.1700

Data Index: 1099130 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2766. Min Act: -0.1700

Data Index: 1004090 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2738. Min Act: -0.1700

Data Index: 660705 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2691. Min Act: -0.1700

Data Index: 847736 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2679. Min Act: -0.1700

Data Index: 721386 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2637. Min Act: -0.1700

Data Index: 933642 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2593. Min Act: -0.1700

Data Index: 65390 (C4 (Web Text))

Max Activating Token Index: 395