Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3674 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.9773. Min Act: -0.0002
Data Index: 710118 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.9456. Min Act: -0.0002
Data Index: 1325371 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.7221. Min Act: -0.0002
Data Index: 910433 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.6481. Min Act: -0.0002
Data Index: 439502 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.7079. Min Act: -0.0002
Data Index: 1376101 (Python Code)
Max Activating Token Index: 526
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.7323. Min Act: -0.0002
Data Index: 61964 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.7783. Min Act: -0.0002
Data Index: 1092749 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.6461. Min Act: -0.0002
Data Index: 762199 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.5401. Min Act: -0.0002
Data Index: 1010786 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.6483. Min Act: -0.0002
Data Index: 848946 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.6413. Min Act: -0.0002
Data Index: 1258116 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.5102. Min Act: -0.0002
Data Index: 267101 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.7355. Min Act: -0.0002
Data Index: 185961 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.4968. Min Act: -0.0002
Data Index: 253169 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.5942. Min Act: -0.0002
Data Index: 273783 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.6360. Min Act: -0.0002
Data Index: 616985 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.5705. Min Act: -0.0002
Data Index: 1042655 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.5486. Min Act: -0.0002
Data Index: 1334088 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.4931. Min Act: -0.0002
Data Index: 323551 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.9773. Min Range: -2.9773
Max Act: 2.5368. Min Act: -0.0002
Data Index: 190294 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full textTruncated
Full Text #19