Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1350 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.1665. Min Act: -0.0001
Data Index: 118952 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.0547. Min Act: -0.0001
Data Index: 1203977 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.2563. Min Act: -0.0001
Data Index: 1211203 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.1036. Min Act: -0.0001
Data Index: 1004918 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.1058. Min Act: -0.0001
Data Index: 848413 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.0156. Min Act: -0.0001
Data Index: 341646 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2563. Min Range: -2.2563
Max Act: 2.0082. Min Act: -0.0001
Data Index: 1148663 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.9197. Min Act: -0.0001
Data Index: 935721 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.9822. Min Act: -0.0001
Data Index: 101610 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.9290. Min Act: -0.0001
Data Index: 1526341 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8284. Min Act: -0.0001
Data Index: 930154 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.9092. Min Act: -0.0001
Data Index: 129745 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8229. Min Act: -0.0001
Data Index: 1241957 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8872. Min Act: -0.0001
Data Index: 573530 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8961. Min Act: -0.0000
Data Index: 1398459 (Python Code)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.9794. Min Act: -0.0001
Data Index: 852136 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8727. Min Act: -0.0001
Data Index: 1316979 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8734. Min Act: -0.0001
Data Index: 967509 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.7143. Min Act: -0.0001
Data Index: 641503 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2563. Min Range: -2.2563
Max Act: 1.8522. Min Act: -0.0001
Data Index: 517430 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19