Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1522 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1907. Min Act: -0.1700
Data Index: 870620 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 339008 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 1330913 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 39563 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1907. Min Act: -0.1700
Data Index: 225074 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 511117 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 286809 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 194189 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1741. Min Act: -0.1700
Data Index: 1185225 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1408. Min Act: -0.1700
Data Index: 518122 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1408. Min Act: -0.1700
Data Index: 960348 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1242. Min Act: -0.1700
Data Index: 84272 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1242. Min Act: -0.1700
Data Index: 968329 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1242. Min Act: -0.1700
Data Index: 781724 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1242. Min Act: -0.1700
Data Index: 107650 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1242. Min Act: -0.1700
Data Index: 17778 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1242. Min Act: -0.1700
Data Index: 81146 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.0907. Min Act: -0.1700
Data Index: 213574 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1074. Min Act: -0.1700
Data Index: 861380 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1907. Min Range: -2.1907
Max Act: 2.1074. Min Act: -0.1700
Data Index: 544473 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19