Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2920 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1927. Min Range: -3.1927
Max Act: 3.1927. Min Act: -0.0001
Data Index: 1027756 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1927. Min Range: -3.1927
Max Act: 3.0955. Min Act: -0.0001
Data Index: 1189400 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1927. Min Range: -3.1927
Max Act: 3.0545. Min Act: -0.0001
Data Index: 1409539 (Python Code)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.7592. Min Act: -0.0001
Data Index: 1389354 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.9950. Min Act: -0.0001
Data Index: 1436226 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.8211. Min Act: -0.0001
Data Index: 1427620 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.8154. Min Act: -0.0001
Data Index: 1365602 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6825. Min Act: -0.0001
Data Index: 1394384 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1927. Min Range: -3.1927
Max Act: 3.0587. Min Act: -0.0001
Data Index: 23161 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6477. Min Act: -0.0001
Data Index: 1519499 (Python Code)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6137. Min Act: -0.0001
Data Index: 1538323 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.5486. Min Act: -0.0001
Data Index: 943954 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6758. Min Act: -0.0001
Data Index: 1646720 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6485. Min Act: -0.0001
Data Index: 578425 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.4042. Min Act: -0.0001
Data Index: 1048236 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6036. Min Act: -0.0000
Data Index: 311393 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.5404. Min Act: -0.0001
Data Index: 1266396 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6735. Min Act: -0.0001
Data Index: 1000713 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.4157. Min Act: -0.0001
Data Index: 1617377 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1927. Min Range: -3.1927
Max Act: 2.6561. Min Act: -0.0001
Data Index: 1433771 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19