Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2207 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.2972. Min Act: -0.0001
Data Index: 386149 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.2511. Min Act: -0.0001
Data Index: 1194446 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.1236. Min Act: -0.0001
Data Index: 603311 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.0569. Min Act: -0.0001
Data Index: 1055236 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.1304. Min Act: -0.0000
Data Index: 703600 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.1112. Min Act: -0.0001
Data Index: 1122629 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.0675. Min Act: -0.0001
Data Index: 331579 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.0287. Min Act: -0.0001
Data Index: 74846 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2972. Min Range: -2.2972
Max Act: 2.0121. Min Act: -0.0001
Data Index: 1068578 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.9669. Min Act: -0.0001
Data Index: 581804 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.7423. Min Act: -0.0001
Data Index: 299346 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.8396. Min Act: -0.0001
Data Index: 89234 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.8082. Min Act: -0.0001
Data Index: 533558 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.8392. Min Act: -0.0001
Data Index: 189108 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.8311. Min Act: -0.0001
Data Index: 1526927 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.6247. Min Act: -0.0001
Data Index: 136222 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.8089. Min Act: -0.0001
Data Index: 26010 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.8643. Min Act: -0.0000
Data Index: 575103 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.6761. Min Act: -0.0000
Data Index: 1524190 (Python Code)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2972. Min Range: -2.2972
Max Act: 1.7889. Min Act: -0.0001
Data Index: 1043550 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19