Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1885 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.2735. Min Act: -0.1700
Data Index: 42633 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.2405. Min Act: -0.1700
Data Index: 1295212 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.2074. Min Act: -0.1700
Data Index: 1289082 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1908. Min Act: -0.1700
Data Index: 797649 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1908. Min Act: -0.1700
Data Index: 447939 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1908. Min Act: -0.1700
Data Index: 1144671 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1575. Min Act: -0.1700
Data Index: 486106 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1575. Min Act: -0.1700
Data Index: 679217 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1409. Min Act: -0.1700
Data Index: 572400 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1409. Min Act: -0.1700
Data Index: 1340816 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1409. Min Act: -0.1700
Data Index: 778516 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1409. Min Act: -0.1700
Data Index: 78002 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1409. Min Act: -0.1700
Data Index: 676198 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1700
Data Index: 608390 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1700
Data Index: 407034 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1700
Data Index: 235356 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1699
Data Index: 329651 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1700
Data Index: 199746 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1700
Data Index: 452066 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2735. Min Range: -2.2735
Max Act: 2.1242. Min Act: -0.1700
Data Index: 786155 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19