Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1985 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0106. Min Act: -0.0001
Data Index: 987047 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0097. Min Act: -0.0001
Data Index: 211840 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0102. Min Act: -0.0001
Data Index: 1327004 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0092. Min Act: -0.0001
Data Index: 44534 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0088. Min Act: -0.0001
Data Index: 511277 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0081. Min Act: -0.0001
Data Index: 87589 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0084. Min Act: -0.0001
Data Index: 1077895 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0070. Min Act: -0.0001
Data Index: 1426347 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0085. Min Act: -0.0001
Data Index: 521381 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0079. Min Act: -0.0001
Data Index: 905701 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0085. Min Act: -0.0001
Data Index: 1142476 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0074. Min Act: -0.0001
Data Index: 1267929 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0081. Min Act: -0.0001
Data Index: 205095 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0073. Min Act: -0.0001
Data Index: 450818 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0077. Min Act: -0.0001
Data Index: 649920 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0070. Min Act: -0.0001
Data Index: 1271995 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0069. Min Act: -0.0001
Data Index: 113380 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0073. Min Act: -0.0001
Data Index: 777834 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0071. Min Act: -0.0001
Data Index: 529330 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0066. Min Act: -0.0001
Data Index: 250626 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19