Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 705 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.2027. Min Act: -0.1700
Data Index: 1066403 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1869. Min Act: -0.1700
Data Index: 36348 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1712. Min Act: -0.1700
Data Index: 726003 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1555. Min Act: -0.1700
Data Index: 107381 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1555. Min Act: -0.1700
Data Index: 371786 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1397. Min Act: -0.1700
Data Index: 211324 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1082. Min Act: -0.1700
Data Index: 37895 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1082. Min Act: -0.1700
Data Index: 1061840 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1239. Min Act: -0.1700
Data Index: 983145 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0924. Min Act: -0.1700
Data Index: 462571 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0766. Min Act: -0.1700
Data Index: 798208 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.1082. Min Act: -0.1700
Data Index: 1096355 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0766. Min Act: -0.1700
Data Index: 1113233 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0924. Min Act: -0.1700
Data Index: 163652 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0766. Min Act: -0.1700
Data Index: 544451 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0766. Min Act: -0.1700
Data Index: 122192 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0766. Min Act: -0.1700
Data Index: 188115 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0766. Min Act: -0.1700
Data Index: 42502 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0609. Min Act: -0.1700
Data Index: 710389 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2027. Min Range: -3.2027
Max Act: 3.0924. Min Act: -0.1700
Data Index: 943537 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19