Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 563 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0963. Min Act: -0.0002
Data Index: 1197376 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0940. Min Act: -0.0003
Data Index: 253609 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0948. Min Act: -0.0003
Data Index: 415040 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0933. Min Act: -0.0002
Data Index: 1243447 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0918. Min Act: -0.0002
Data Index: 185233 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0903. Min Act: -0.0002
Data Index: 483197 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0857. Min Act: -0.0002
Data Index: 455424 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0904. Min Act: -0.0003
Data Index: 1328796 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0868. Min Act: -0.0002
Data Index: 1513337 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0863. Min Act: -0.0002
Data Index: 1281783 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0846. Min Act: -0.0002
Data Index: 979786 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0824. Min Act: -0.0002
Data Index: 1041141 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0857. Min Act: -0.0003
Data Index: 972505 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0868. Min Act: -0.0003
Data Index: 550979 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0905. Min Act: -0.0002
Data Index: 384331 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0865. Min Act: -0.0002
Data Index: 324449 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0850. Min Act: -0.0003
Data Index: 584512 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0881. Min Act: -0.0002
Data Index: 971216 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0847. Min Act: -0.0002
Data Index: 699477 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0963. Min Range: -0.0963
Max Act: 0.0845. Min Act: -0.0002
Data Index: 1513305 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19