Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1736 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.2021. Min Act: -0.0002
Data Index: 194683 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1876. Min Act: -0.0002
Data Index: 430656 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1567. Min Act: -0.0002
Data Index: 1238387 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1518. Min Act: -0.0002
Data Index: 1276096 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1510. Min Act: -0.0002
Data Index: 1215534 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1558. Min Act: -0.0002
Data Index: 162862 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1483. Min Act: -0.0002
Data Index: 107313 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1447. Min Act: -0.0002
Data Index: 473438 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1464. Min Act: -0.0002
Data Index: 951368 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1416. Min Act: -0.0002
Data Index: 658539 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1398. Min Act: -0.0002
Data Index: 676651 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1465. Min Act: -0.0002
Data Index: 450683 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1433. Min Act: -0.0002
Data Index: 271512 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1425. Min Act: -0.0002
Data Index: 866041 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1448. Min Act: -0.0002
Data Index: 1229466 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1384. Min Act: -0.0002
Data Index: 1284707 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1382. Min Act: -0.0002
Data Index: 470285 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1422. Min Act: -0.0002
Data Index: 659373 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1370. Min Act: -0.0002
Data Index: 730688 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 0.2021. Min Range: -0.2021
Max Act: 0.1368. Min Act: -0.0002
Data Index: 216982 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full textTruncated
Full Text #19