Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3887 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.4554. Min Act: -0.0001
Data Index: 55179 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1768. Min Act: -0.0001
Data Index: 563177 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.2501. Min Act: -0.0001
Data Index: 1193350 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.2153. Min Act: -0.0001
Data Index: 1249029 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1663. Min Act: -0.0001
Data Index: 474437 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1902. Min Act: -0.0001
Data Index: 1220929 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1757. Min Act: -0.0001
Data Index: 1216258 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1391. Min Act: -0.0001
Data Index: 1160574 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1268. Min Act: -0.0001
Data Index: 466067 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4554. Min Range: -1.4554
Max Act: 0.9881. Min Act: -0.0001
Data Index: 150541 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.0139. Min Act: -0.0001
Data Index: 423959 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1258. Min Act: -0.0001
Data Index: 300663 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.0761. Min Act: -0.0001
Data Index: 386712 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1647. Min Act: -0.0001
Data Index: 603021 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4554. Min Range: -1.4554
Max Act: 0.9510. Min Act: -0.0001
Data Index: 1042418 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.0972. Min Act: -0.0001
Data Index: 444933 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1163. Min Act: -0.0001
Data Index: 616239 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.1000. Min Act: -0.0001
Data Index: 117193 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4554. Min Range: -1.4554
Max Act: 1.0918. Min Act: -0.0001
Data Index: 517905 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4554. Min Range: -1.4554
Max Act: 0.9929. Min Act: -0.0001
Data Index: 500842 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19