Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3960 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0084. Min Act: -0.0003
Data Index: 1040537 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0080. Min Act: -0.0004
Data Index: 1373901 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0083. Min Act: -0.0003
Data Index: 87247 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0070. Min Act: -0.0003
Data Index: 645659 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0057. Min Act: -0.0003
Data Index: 67484 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0076. Min Act: -0.0003
Data Index: 689177 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0078. Min Act: -0.0003
Data Index: 45089 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0068. Min Act: -0.0003
Data Index: 903039 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0063. Min Act: -0.0003
Data Index: 660990 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0073. Min Act: -0.0003
Data Index: 1315794 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0071. Min Act: -0.0003
Data Index: 263624 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0064. Min Act: -0.0004
Data Index: 43461 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0072. Min Act: -0.0003
Data Index: 783024 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0067. Min Act: -0.0003
Data Index: 1013110 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0070. Min Act: -0.0003
Data Index: 545537 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0064. Min Act: -0.0003
Data Index: 25665 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0063. Min Act: -0.0003
Data Index: 1129571 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0068. Min Act: -0.0003
Data Index: 1133899 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0069. Min Act: -0.0003
Data Index: 1508660 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0084. Min Range: -0.0084
Max Act: 0.0061. Min Act: -0.0003
Data Index: 740826 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19