Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1820 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7890. Min Act: -0.1697
Data Index: 172110 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7571. Min Act: -0.1697
Data Index: 1034088 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7411. Min Act: -0.1699
Data Index: 1054032 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7571. Min Act: -0.1697
Data Index: 818511 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7251. Min Act: -0.1699
Data Index: 1024812 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7091. Min Act: -0.1700
Data Index: 1203917 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7091. Min Act: -0.1698
Data Index: 721472 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7091. Min Act: -0.1699
Data Index: 592264 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6931. Min Act: -0.1700
Data Index: 397327 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7091. Min Act: -0.1700
Data Index: 1046920 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.7091. Min Act: -0.1700
Data Index: 709158 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6931. Min Act: -0.1700
Data Index: 1352139 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6931. Min Act: -0.1700
Data Index: 1293339 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6931. Min Act: -0.1700
Data Index: 527821 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6771. Min Act: -0.1699
Data Index: 1093214 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6771. Min Act: -0.1700
Data Index: 696897 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6611. Min Act: -0.1697
Data Index: 1215880 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6931. Min Act: -0.1700
Data Index: 643000 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6771. Min Act: -0.1697
Data Index: 788196 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7890. Min Range: -2.7890
Max Act: 2.6771. Min Act: -0.1697
Data Index: 583879 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19