Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 264 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.9137. Min Act: -0.1700
Data Index: 933809 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.8502. Min Act: -0.1700
Data Index: 107514 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.8184. Min Act: -0.1700
Data Index: 711653 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.8025. Min Act: -0.1700
Data Index: 604517 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.7706. Min Act: -0.1700
Data Index: 255143 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.7387. Min Act: -0.1700
Data Index: 790260 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.7067. Min Act: -0.1700
Data Index: 500715 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6747. Min Act: -0.1700
Data Index: 1105932 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6907. Min Act: -0.1700
Data Index: 360404 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6907. Min Act: -0.1700
Data Index: 603512 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6747. Min Act: -0.1700
Data Index: 166651 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6586. Min Act: -0.1700
Data Index: 549717 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6907. Min Act: -0.1700
Data Index: 1231981 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6586. Min Act: -0.1700
Data Index: 742895 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6586. Min Act: -0.1700
Data Index: 1243159 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6426. Min Act: -0.1700
Data Index: 1190515 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6586. Min Act: -0.1700
Data Index: 932559 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6426. Min Act: -0.1700
Data Index: 760341 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6426. Min Act: -0.1700
Data Index: 342378 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9137. Min Range: -2.9137
Max Act: 2.6426. Min Act: -0.1700
Data Index: 218915 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19