Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1679 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.7712. Min Act: -0.1700
Data Index: 449814 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.7553. Min Act: -0.1700
Data Index: 536076 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6913. Min Act: -0.1700
Data Index: 1256125 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6753. Min Act: -0.1700
Data Index: 188529 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6753. Min Act: -0.1700
Data Index: 967132 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6593. Min Act: -0.1700
Data Index: 1216672 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6432. Min Act: -0.1700
Data Index: 397902 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6432. Min Act: -0.1700
Data Index: 1036153 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6432. Min Act: -0.1700
Data Index: 446879 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6272. Min Act: -0.1700
Data Index: 1089188 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6111. Min Act: -0.1700
Data Index: 498697 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.6111. Min Act: -0.1700
Data Index: 1055284 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5789. Min Act: -0.1700
Data Index: 504270 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5467. Min Act: -0.1700
Data Index: 465260 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5628. Min Act: -0.1700
Data Index: 86324 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5628. Min Act: -0.1700
Data Index: 1052392 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5305. Min Act: -0.1700
Data Index: 558849 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5305. Min Act: -0.1700
Data Index: 1178300 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5305. Min Act: -0.1700
Data Index: 679030 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7712. Min Range: -2.7712
Max Act: 2.5143. Min Act: -0.1700
Data Index: 976112 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19