Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 644 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6917. Min Act: -0.0001
Data Index: 778835 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6759. Min Act: -0.0001
Data Index: 996039 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6688. Min Act: -0.0001
Data Index: 1364623 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6426. Min Act: -0.0001
Data Index: 855333 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6470. Min Act: -0.0001
Data Index: 963974 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6210. Min Act: -0.0001
Data Index: 1092795 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6384. Min Act: -0.0001
Data Index: 852606 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6354. Min Act: -0.0001
Data Index: 1163042 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6258. Min Act: -0.0001
Data Index: 1616338 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6260. Min Act: -0.0001
Data Index: 634058 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6350. Min Act: -0.0001
Data Index: 827062 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6107. Min Act: -0.0001
Data Index: 408189 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.5886. Min Act: -0.0001
Data Index: 699284 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.5687. Min Act: -0.0001
Data Index: 126321 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6026. Min Act: -0.0001
Data Index: 338111 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.5848. Min Act: -0.0001
Data Index: 265337 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.6004. Min Act: -0.0001
Data Index: 1109384 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.5680. Min Act: -0.0001
Data Index: 1097333 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.5647. Min Act: -0.0001
Data Index: 345368 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6917. Min Range: -0.6917
Max Act: 0.5657. Min Act: -0.0001
Data Index: 85434 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19