Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 845 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.6741. Min Act: -0.1700
Data Index: 875532 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5491. Min Act: -0.1700
Data Index: 763395 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5803. Min Act: -0.1700
Data Index: 714887 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.6116. Min Act: -0.1700
Data Index: 585654 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5491. Min Act: -0.1700
Data Index: 318116 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5491. Min Act: -0.1700
Data Index: 426545 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5491. Min Act: -0.1700
Data Index: 1138013 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5178. Min Act: -0.1700
Data Index: 40530 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 1356079 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 614037 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5178. Min Act: -0.1700
Data Index: 1212560 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 1300241 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.5178. Min Act: -0.1700
Data Index: 864229 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 810154 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 1174621 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 19503 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4553. Min Act: -0.1700
Data Index: 627163 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 227214 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4866. Min Act: -0.1700
Data Index: 491168 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6741. Min Range: -4.6741
Max Act: 4.4553. Min Act: -0.1700
Data Index: 114799 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19