Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.4091. Min Act: -0.0001
Data Index: 458249 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.4038. Min Act: -0.0001
Data Index: 343247 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3814. Min Act: -0.0001
Data Index: 737138 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3732. Min Act: -0.0001
Data Index: 1118773 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3258. Min Act: -0.0001
Data Index: 1106678 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3359. Min Act: -0.0001
Data Index: 75261 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3273. Min Act: -0.0001
Data Index: 490712 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3053. Min Act: -0.0001
Data Index: 882010 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2886. Min Act: -0.0001
Data Index: 1084666 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2990. Min Act: -0.0001
Data Index: 1123189 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2764. Min Act: -0.0001
Data Index: 1184546 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3085. Min Act: -0.0001
Data Index: 917368 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.3014. Min Act: -0.0001
Data Index: 442549 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2848. Min Act: -0.0001
Data Index: 736718 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2942. Min Act: -0.0001
Data Index: 78417 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2916. Min Act: -0.0001
Data Index: 747184 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2868. Min Act: -0.0001
Data Index: 133167 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2849. Min Act: -0.0001
Data Index: 804757 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2957. Min Act: -0.0001
Data Index: 1249790 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4091. Min Range: -0.4091
Max Act: 0.2777. Min Act: -0.0001
Data Index: 632007 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19