Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1064 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0046. Min Range: -2.0046
Max Act: 2.0046. Min Act: -0.0001
Data Index: 426142 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0046. Min Range: -2.0046
Max Act: 2.0046. Min Act: -0.0001
Data Index: 1460372 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0046. Min Range: -2.0046
Max Act: 2.0046. Min Act: -0.0001
Data Index: 1415876 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.5422. Min Act: -0.0001
Data Index: 469622 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.1836. Min Act: -0.0001
Data Index: 1474694 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.3043. Min Act: -0.0001
Data Index: 239654 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2216. Min Act: -0.0001
Data Index: 152441 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.3204. Min Act: -0.0001
Data Index: 1306418 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2824. Min Act: -0.0001
Data Index: 1120344 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2980. Min Act: -0.0001
Data Index: 48288 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2926. Min Act: -0.0001
Data Index: 1525194 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.0967. Min Act: -0.0001
Data Index: 326394 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.3102. Min Act: -0.0001
Data Index: 1570852 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2352. Min Act: -0.0001
Data Index: 399600 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2992. Min Act: -0.0001
Data Index: 481913 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2169. Min Act: -0.0001
Data Index: 1473022 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.1929. Min Act: -0.0001
Data Index: 794426 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.3170. Min Act: -0.0001
Data Index: 185624 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.2995. Min Act: -0.0001
Data Index: 1655450 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0046. Min Range: -2.0046
Max Act: 1.1497. Min Act: -0.0001
Data Index: 644651 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19