Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1945 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 1099799 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.9012. Min Act: -0.1700
Data Index: 754454 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.7449. Min Act: -0.1700
Data Index: 153882 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.6199. Min Act: -0.1700
Data Index: 457554 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.5574. Min Act: -0.1700
Data Index: 578368 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.5261. Min Act: -0.1700
Data Index: 338517 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.4949. Min Act: -0.1700
Data Index: 96538 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.3699. Min Act: -0.1700
Data Index: 924623 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.3699. Min Act: -0.1700
Data Index: 625219 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.3074. Min Act: -0.1700
Data Index: 728975 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.2449. Min Act: -0.1700
Data Index: 141538 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.3074. Min Act: -0.1700
Data Index: 81766 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.2761. Min Act: -0.1699
Data Index: 1333233 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.2449. Min Act: -0.1700
Data Index: 820777 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.2449. Min Act: -0.1699
Data Index: 183654 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.1823. Min Act: -0.1700
Data Index: 540206 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.1823. Min Act: -0.1700
Data Index: 1267997 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.1823. Min Act: -0.1700
Data Index: 1244863 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.1823. Min Act: -0.1700
Data Index: 375328 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9012. Min Range: -4.9012
Max Act: 4.2136. Min Act: -0.1700
Data Index: 898630 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19