Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1717 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.3586. Min Act: -0.1700
Data Index: 116035 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.3422. Min Act: -0.1700
Data Index: 679156 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.3258. Min Act: -0.1700
Data Index: 26638 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.3094. Min Act: -0.1700
Data Index: 78847 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2765. Min Act: -0.1700
Data Index: 1136426 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2929. Min Act: -0.1700
Data Index: 490596 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2929. Min Act: -0.1700
Data Index: 204488 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2765. Min Act: -0.1700
Data Index: 909152 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2765. Min Act: -0.1700
Data Index: 200565 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2765. Min Act: -0.1700
Data Index: 252813 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2765. Min Act: -0.1700
Data Index: 1074456 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2765. Min Act: -0.1700
Data Index: 861516 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2600. Min Act: -0.1700
Data Index: 1099660 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2600. Min Act: -0.1700
Data Index: 82075 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2600. Min Act: -0.1700
Data Index: 935420 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2435. Min Act: -0.1700
Data Index: 703674 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2600. Min Act: -0.1700
Data Index: 399430 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2600. Min Act: -0.1700
Data Index: 900991 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2435. Min Act: -0.1700
Data Index: 669172 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3586. Min Range: -2.3586
Max Act: 2.2600. Min Act: -0.1700
Data Index: 638856 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19