Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4130 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0630. Min Act: -0.0002
Data Index: 608036 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0599. Min Act: -0.0002
Data Index: 27926 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0576. Min Act: -0.0002
Data Index: 260100 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0565. Min Act: -0.0002
Data Index: 232641 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0548. Min Act: -0.0002
Data Index: 166923 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0526. Min Act: -0.0002
Data Index: 603934 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0480. Min Act: -0.0002
Data Index: 162395 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0501. Min Act: -0.0002
Data Index: 1213328 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0458. Min Act: -0.0002
Data Index: 1129047 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0476. Min Act: -0.0002
Data Index: 477466 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0451. Min Act: -0.0002
Data Index: 980133 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0443. Min Act: -0.0002
Data Index: 344061 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0456. Min Act: -0.0002
Data Index: 822915 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0470. Min Act: -0.0002
Data Index: 1057425 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0471. Min Act: -0.0002
Data Index: 1304297 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0448. Min Act: -0.0002
Data Index: 1202703 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0451. Min Act: -0.0002
Data Index: 571862 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0453. Min Act: -0.0002
Data Index: 1100916 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0411. Min Act: -0.0002
Data Index: 595941 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 0.0630. Min Range: -0.0630
Max Act: 0.0426. Min Act: -0.0002
Data Index: 1274503 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full textTruncated
Full Text #19