Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1965 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1717. Min Act: -0.1700
Data Index: 1207042 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1717. Min Act: -0.1700
Data Index: 1156000 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1551. Min Act: -0.1700
Data Index: 1255563 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1717. Min Act: -0.1700
Data Index: 1145659 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1384. Min Act: -0.1700
Data Index: 306046 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0966. Min Act: -0.1700
Data Index: 923403 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1050. Min Act: -0.1700
Data Index: 1266039 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1050. Min Act: -0.1700
Data Index: 19535 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.1134. Min Act: -0.1700
Data Index: 1303686 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0966. Min Act: -0.1700
Data Index: 316787 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0883. Min Act: -0.1700
Data Index: 1026368 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0883. Min Act: -0.1700
Data Index: 428831 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0883. Min Act: -0.1700
Data Index: 1235805 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0715. Min Act: -0.1700
Data Index: 1223545 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0799. Min Act: -0.1700
Data Index: 173278 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0715. Min Act: -0.1700
Data Index: 778092 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0547. Min Act: -0.1700
Data Index: 1337767 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0463. Min Act: -0.1700
Data Index: 953655 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0715. Min Act: -0.1700
Data Index: 694258 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1717. Min Range: -2.1717
Max Act: 2.0547. Min Act: -0.1700
Data Index: 28645 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19