Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 88 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.6541. Min Act: -0.0001
Data Index: 758934 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.6120. Min Act: -0.0001
Data Index: 1207608 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.7860. Min Act: -0.0001
Data Index: 1340616 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.5595. Min Act: -0.0001
Data Index: 992240 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.6018. Min Act: -0.0001
Data Index: 850727 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.4945. Min Act: -0.0001
Data Index: 648643 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.6101. Min Act: -0.0001
Data Index: 1270874 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.5643. Min Act: -0.0001
Data Index: 1312140 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.5281. Min Act: -0.0001
Data Index: 780837 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.4597. Min Act: -0.0001
Data Index: 217482 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.5258. Min Act: -0.0001
Data Index: 140489 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.5014. Min Act: -0.0001
Data Index: 1020114 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.4876. Min Act: -0.0001
Data Index: 1327453 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.5139. Min Act: -0.0001
Data Index: 538971 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.4753. Min Act: -0.0001
Data Index: 617074 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.3588. Min Act: -0.0001
Data Index: 1136732 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.4098. Min Act: -0.0001
Data Index: 1019614 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.4037. Min Act: -0.0001
Data Index: 1006384 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.3542. Min Act: -0.0001
Data Index: 848490 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7860. Min Range: -1.7860
Max Act: 1.3049. Min Act: -0.0001
Data Index: 629796 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19