Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 154 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.5566. Min Act: -0.1700
Data Index: 224769 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.5405. Min Act: -0.1700
Data Index: 1278359 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.5082. Min Act: -0.1700
Data Index: 507563 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.5082. Min Act: -0.1700
Data Index: 1117831 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4757. Min Act: -0.1700
Data Index: 1314125 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4270. Min Act: -0.1700
Data Index: 627963 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4433. Min Act: -0.1700
Data Index: 339514 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4433. Min Act: -0.1700
Data Index: 109589 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4433. Min Act: -0.1700
Data Index: 1017866 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4433. Min Act: -0.1700
Data Index: 1446326 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4270. Min Act: -0.1700
Data Index: 300282 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4433. Min Act: -0.1700
Data Index: 349311 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4107. Min Act: -0.1700
Data Index: 1000107 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4107. Min Act: -0.1700
Data Index: 871337 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4270. Min Act: -0.1700
Data Index: 1194495 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4107. Min Act: -0.1700
Data Index: 1066830 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4107. Min Act: -0.1700
Data Index: 694387 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4107. Min Act: -0.1700
Data Index: 877215 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.4107. Min Act: -0.1700
Data Index: 209186 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5566. Min Range: -2.5566
Max Act: 2.3781. Min Act: -0.1700
Data Index: 1165023 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19