Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1915 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0005. Min Range: -4.0005
Max Act: 4.0005. Min Act: -0.1700
Data Index: 589107 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.9692. Min Act: -0.1700
Data Index: 622083 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.8754. Min Act: -0.1700
Data Index: 624825 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.9067. Min Act: -0.1700
Data Index: 140918 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.8754. Min Act: -0.1700
Data Index: 399767 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.8754. Min Act: -0.1700
Data Index: 1253184 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.8129. Min Act: -0.1700
Data Index: 757326 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7816. Min Act: -0.1700
Data Index: 834967 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7816. Min Act: -0.1700
Data Index: 1041562 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7816. Min Act: -0.1700
Data Index: 1335760 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7816. Min Act: -0.1700
Data Index: 1031860 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7503. Min Act: -0.1700
Data Index: 476779 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7190. Min Act: -0.1700
Data Index: 816980 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.6877. Min Act: -0.1700
Data Index: 155651 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.6877. Min Act: -0.1700
Data Index: 1285457 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.6877. Min Act: -0.1700
Data Index: 495567 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.7190. Min Act: -0.1700
Data Index: 479605 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.6877. Min Act: -0.1700
Data Index: 14892 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.6877. Min Act: -0.1700
Data Index: 347717 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0005. Min Range: -4.0005
Max Act: 3.6564. Min Act: -0.1700
Data Index: 74793 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19