Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1487 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.8904. Min Act: -0.1700
Data Index: 105190 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.3592. Min Act: -0.1699
Data Index: 500088 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.3279. Min Act: -0.1700
Data Index: 125659 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.2967. Min Act: -0.1700
Data Index: 706418 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.1404. Min Act: -0.1700
Data Index: 719794 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.1717. Min Act: -0.1700
Data Index: 214239 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.0779. Min Act: -0.1700
Data Index: 125516 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.0779. Min Act: -0.1700
Data Index: 1067753 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8904. Min Range: -6.8904
Max Act: 6.1092. Min Act: -0.1700
Data Index: 790071 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.9842. Min Act: -0.1695
Data Index: 1014173 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.9842. Min Act: -0.1700
Data Index: 945302 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.9842. Min Act: -0.1700
Data Index: 384391 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.9529. Min Act: -0.1700
Data Index: 168013 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.9842. Min Act: -0.1694
Data Index: 202035 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.8904. Min Act: -0.1700
Data Index: 1135745 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.8904. Min Act: -0.1700
Data Index: 619795 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.8904. Min Act: -0.1700
Data Index: 1042585 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.8279. Min Act: -0.1697
Data Index: 145264 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.8904. Min Act: -0.1700
Data Index: 592581 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8904. Min Range: -6.8904
Max Act: 5.8904. Min Act: -0.1700
Data Index: 146261 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19