Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 297 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 22.1841. Min Range: -22.1841
Max Act: 22.1841. Min Act: -0.0002
Data Index: 1403559 (Python Code)
Max Activating Token Index: 177
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.9342. Min Act: -0.0002
Data Index: 1418561 (Python Code)
Max Activating Token Index: 823
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.9341. Min Act: -0.0002
Data Index: 1118162 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.9340. Min Act: -0.0002
Data Index: 729057 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6840. Min Act: -0.0002
Data Index: 705592 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.8090. Min Act: -0.0002
Data Index: 1155121 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.8090. Min Act: -0.0002
Data Index: 941774 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.8089. Min Act: -0.0002
Data Index: 352290 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.8090. Min Act: -0.0002
Data Index: 922332 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.8089. Min Act: -0.0002
Data Index: 1221428 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.8088. Min Act: -0.0002
Data Index: 284618 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6841. Min Act: -0.0002
Data Index: 336967 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6841. Min Act: -0.0002
Data Index: 968089 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6841. Min Act: -0.0002
Data Index: 862878 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6840. Min Act: -0.0002
Data Index: 274282 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6840. Min Act: -0.0002
Data Index: 1504792 (Python Code)
Max Activating Token Index: 292
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6840. Min Act: -0.0002
Data Index: 728389 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6840. Min Act: -0.0002
Data Index: 198398 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6839. Min Act: -0.0002
Data Index: 888071 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 22.1841. Min Range: -22.1841
Max Act: 21.6840. Min Act: -0.0002
Data Index: 86839 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full textTruncated
Full Text #19