Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.6592. Min Act: -0.0001
Data Index: 171706 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.4562. Min Act: -0.0001
Data Index: 632709 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.0876. Min Act: -0.0001
Data Index: 833340 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.4262. Min Act: -0.0001
Data Index: 607895 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.1599. Min Act: -0.0001
Data Index: 908354 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.3458. Min Act: -0.0001
Data Index: 1303260 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.1049. Min Act: -0.0001
Data Index: 1101418 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6592. Min Range: -2.6592
Max Act: 2.1000. Min Act: -0.0001
Data Index: 229584 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.9152. Min Act: -0.0001
Data Index: 489236 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.8821. Min Act: -0.0001
Data Index: 269509 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.7130. Min Act: -0.0001
Data Index: 1233934 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.9095. Min Act: -0.0001
Data Index: 523369 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.7005. Min Act: -0.0001
Data Index: 812035 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.5292. Min Act: -0.0001
Data Index: 438217 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.8383. Min Act: -0.0001
Data Index: 1211374 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.7270. Min Act: -0.0001
Data Index: 225525 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.7117. Min Act: -0.0001
Data Index: 220492 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.7088. Min Act: -0.0001
Data Index: 1013638 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.7628. Min Act: -0.0001
Data Index: 250816 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6592. Min Range: -2.6592
Max Act: 1.9419. Min Act: -0.0001
Data Index: 1151032 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19