Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 855 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.1192. Min Range: -6.1192
Max Act: 6.1192. Min Act: -0.1700
Data Index: 36320 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1192. Min Range: -6.1192
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1050013 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1266963 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.8692. Min Act: -0.1700
Data Index: 829617 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.8692. Min Act: -0.1700
Data Index: 160666 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.8692. Min Act: -0.1700
Data Index: 322397 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7754. Min Act: -0.1700
Data Index: 230660 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7754. Min Act: -0.1700
Data Index: 1218150 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7129. Min Act: -0.1700
Data Index: 630067 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7754. Min Act: -0.1700
Data Index: 313104 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7129. Min Act: -0.1700
Data Index: 43382 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7442. Min Act: -0.1700
Data Index: 662849 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7442. Min Act: -0.1700
Data Index: 793733 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.6817. Min Act: -0.1700
Data Index: 814488 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.7129. Min Act: -0.1700
Data Index: 966078 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.6504. Min Act: -0.1700
Data Index: 340148 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.6504. Min Act: -0.1700
Data Index: 1097340 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.6504. Min Act: -0.1700
Data Index: 1064089 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.6192. Min Act: -0.1699
Data Index: 242920 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1192. Min Range: -6.1192
Max Act: 5.6192. Min Act: -0.1700
Data Index: 979900 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19