Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1283 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1036. Min Range: -3.1036
Max Act: 3.1036. Min Act: -0.1700
Data Index: 655784 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1036. Min Range: -3.1036
Max Act: 3.0247. Min Act: -0.1700
Data Index: 498510 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1036. Min Range: -3.1036
Max Act: 3.0089. Min Act: -0.1700
Data Index: 593486 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9773. Min Act: -0.1700
Data Index: 622443 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9773. Min Act: -0.1700
Data Index: 254449 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9614. Min Act: -0.1700
Data Index: 41669 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9614. Min Act: -0.1700
Data Index: 1333854 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9614. Min Act: -0.1700
Data Index: 356371 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9456. Min Act: -0.1700
Data Index: 1270024 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9614. Min Act: -0.1700
Data Index: 1188448 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9614. Min Act: -0.1700
Data Index: 980065 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9456. Min Act: -0.1700
Data Index: 867052 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9614. Min Act: -0.1700
Data Index: 575978 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9456. Min Act: -0.1700
Data Index: 76406 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9456. Min Act: -0.1700
Data Index: 442805 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9456. Min Act: -0.1700
Data Index: 362246 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9456. Min Act: -0.1700
Data Index: 319692 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9298. Min Act: -0.1700
Data Index: 358926 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9298. Min Act: -0.1700
Data Index: 160268 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1036. Min Range: -3.1036
Max Act: 2.9139. Min Act: -0.1700
Data Index: 568460 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19