Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 919 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.4266. Min Act: -0.1700
Data Index: 309010 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.4266. Min Act: -0.1700
Data Index: 1352748 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.4103. Min Act: -0.1700
Data Index: 35231 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.3286. Min Act: -0.1700
Data Index: 528892 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2793. Min Act: -0.1699
Data Index: 97041 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2628. Min Act: -0.1699
Data Index: 974518 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2628. Min Act: -0.1700
Data Index: 680914 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2463. Min Act: -0.1698
Data Index: 197979 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2298. Min Act: -0.1700
Data Index: 766074 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2298. Min Act: -0.1700
Data Index: 948854 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2298. Min Act: -0.1700
Data Index: 618359 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2132. Min Act: -0.1700
Data Index: 277481 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2298. Min Act: -0.1699
Data Index: 635515 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2298. Min Act: -0.1700
Data Index: 1280883 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2132. Min Act: -0.1700
Data Index: 73614 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.2132. Min Act: -0.1700
Data Index: 903569 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.1800. Min Act: -0.1699
Data Index: 148729 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.1966. Min Act: -0.1699
Data Index: 1083886 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.1800. Min Act: -0.1700
Data Index: 859254 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4266. Min Range: -2.4266
Max Act: 2.1800. Min Act: -0.1700
Data Index: 231215 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19