Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2049 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0727. Min Range: -2.0727
Max Act: 2.0727. Min Act: -0.0001
Data Index: 1639620 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.8191. Min Act: -0.0001
Data Index: 934975 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7732. Min Act: -0.0001
Data Index: 666300 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.8516. Min Act: -0.0001
Data Index: 897771 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7029. Min Act: -0.0001
Data Index: 1603625 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7709. Min Act: -0.0001
Data Index: 1407021 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7690. Min Act: -0.0001
Data Index: 1535637 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7470. Min Act: -0.0001
Data Index: 1556823 (Python Code)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7287. Min Act: -0.0001
Data Index: 1494293 (Python Code)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.6931. Min Act: -0.0001
Data Index: 1509869 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7944. Min Act: -0.0001
Data Index: 1599287 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.8004. Min Act: -0.0001
Data Index: 1393909 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7027. Min Act: -0.0001
Data Index: 1562897 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.7560. Min Act: -0.0001
Data Index: 1486889 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.6033. Min Act: -0.0001
Data Index: 879509 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.5530. Min Act: -0.0001
Data Index: 1538210 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.5246. Min Act: -0.0001
Data Index: 1601568 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.6934. Min Act: -0.0001
Data Index: 1381932 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.6035. Min Act: -0.0001
Data Index: 1533436 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0727. Min Range: -2.0727
Max Act: 1.4603. Min Act: -0.0001
Data Index: 1539317 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19