Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 340 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6389. Min Act: -0.1700
Data Index: 579619 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6702. Min Act: -0.1700
Data Index: 345917 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6389. Min Act: -0.1700
Data Index: 632468 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6389. Min Act: -0.1700
Data Index: 1067112 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6389. Min Act: -0.1700
Data Index: 1097037 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6077. Min Act: -0.1700
Data Index: 722602 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6077. Min Act: -0.1700
Data Index: 1102255 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6077. Min Act: -0.1700
Data Index: 356972 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6077. Min Act: -0.1700
Data Index: 1183455 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.6077. Min Act: -0.1700
Data Index: 163140 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 486673 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5764. Min Act: -0.1700
Data Index: 130055 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 805196 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 963692 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 980377 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 456600 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5139. Min Act: -0.1700
Data Index: 125928 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5139. Min Act: -0.1700
Data Index: 983764 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 389858 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6702. Min Range: -4.6702
Max Act: 4.5452. Min Act: -0.1700
Data Index: 125703 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19