Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 711 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0054. Min Act: -0.0004
Data Index: 68087 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0048. Min Act: -0.0004
Data Index: 510939 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0048. Min Act: -0.0003
Data Index: 1524194 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0048. Min Act: -0.0003
Data Index: 55095 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0048. Min Act: -0.0003
Data Index: 524181 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0048. Min Act: -0.0003
Data Index: 317673 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0047. Min Act: -0.0003
Data Index: 1508229 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0047. Min Act: -0.0003
Data Index: 185600 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0046. Min Act: -0.0003
Data Index: 1560755 (Python Code)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0003
Data Index: 1081705 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0004
Data Index: 1190689 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0004
Data Index: 559401 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0003
Data Index: 1539084 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0003
Data Index: 192703 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0004
Data Index: 1054172 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0045. Min Act: -0.0004
Data Index: 1049659 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0044. Min Act: -0.0004
Data Index: 917065 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0044. Min Act: -0.0003
Data Index: 1633427 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0044. Min Act: -0.0003
Data Index: 1361369 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0054. Min Range: -0.0054
Max Act: 0.0044. Min Act: -0.0003
Data Index: 1403485 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19