Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2661 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.3072. Min Act: -0.0001
Data Index: 1290175 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.1530. Min Act: -0.0001
Data Index: 887281 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.1713. Min Act: -0.0001
Data Index: 1113299 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.1120. Min Act: -0.0001
Data Index: 143138 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.1283. Min Act: -0.0001
Data Index: 85421 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.1148. Min Act: -0.0001
Data Index: 7614 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0954. Min Act: -0.0001
Data Index: 1278898 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0185. Min Act: -0.0001
Data Index: 937622 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.1197. Min Act: -0.0001
Data Index: 483317 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0481. Min Act: -0.0001
Data Index: 146522 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0818. Min Act: -0.0001
Data Index: 787473 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3072. Min Range: -1.3072
Max Act: 0.9972. Min Act: -0.0001
Data Index: 1390497 (Python Code)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0485. Min Act: -0.0001
Data Index: 966172 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0333. Min Act: -0.0001
Data Index: 282825 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0965. Min Act: -0.0001
Data Index: 650918 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0324. Min Act: -0.0001
Data Index: 51759 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0036. Min Act: -0.0001
Data Index: 87251 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0073. Min Act: -0.0001
Data Index: 1319318 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0605. Min Act: -0.0001
Data Index: 1228648 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3072. Min Range: -1.3072
Max Act: 1.0239. Min Act: -0.0001
Data Index: 107502 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19