Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1197 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.7012. Min Act: -0.1700
Data Index: 330596 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.7012. Min Act: -0.1700
Data Index: 589306 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.7012. Min Act: -0.1700
Data Index: 1113363 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.7012. Min Act: -0.1700
Data Index: 1038789 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6852. Min Act: -0.1700
Data Index: 936922 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6852. Min Act: -0.1700
Data Index: 493545 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.7012. Min Act: -0.1700
Data Index: 774703 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.7012. Min Act: -0.1700
Data Index: 139261 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6691. Min Act: -0.1700
Data Index: 1126431 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6852. Min Act: -0.1700
Data Index: 887008 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6691. Min Act: -0.1700
Data Index: 536913 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6691. Min Act: -0.1700
Data Index: 859222 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 230947 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 1146013 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 984570 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 783377 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 250267 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 965452 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 72320 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7012. Min Range: -2.7012
Max Act: 2.6531. Min Act: -0.1700
Data Index: 693867 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19