Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4481 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.3714. Min Act: -0.0001
Data Index: 959926 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.3843. Min Act: -0.0001
Data Index: 37378 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1325. Min Act: -0.0001
Data Index: 454950 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1057. Min Act: -0.0001
Data Index: 600933 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.2361. Min Act: -0.0002
Data Index: 96851 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1000. Min Act: -0.0001
Data Index: 593726 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.2558. Min Act: -0.0001
Data Index: 1318258 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.3132. Min Act: -0.0001
Data Index: 1099528 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.4483. Min Act: -0.0001
Data Index: 1006116 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.3591. Min Act: -0.0001
Data Index: 1272443 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1090. Min Act: -0.0001
Data Index: 409453 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.2994. Min Act: -0.0001
Data Index: 388384 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.2218. Min Act: -0.0002
Data Index: 1129511 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.2828. Min Act: -0.0001
Data Index: 744494 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1136. Min Act: -0.0002
Data Index: 533683 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1626. Min Act: -0.0001
Data Index: 1000093 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1808. Min Act: -0.0001
Data Index: 1066077 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1166. Min Act: -0.0001
Data Index: 337033 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.2474. Min Act: -0.0001
Data Index: 368295 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4483. Min Range: -1.4483
Max Act: 1.1711. Min Act: -0.0001
Data Index: 901742 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19