Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 168 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.7470. Min Act: -0.0001
Data Index: 272697 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.6716. Min Act: -0.0001
Data Index: 219811 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.3455. Min Act: -0.0001
Data Index: 910357 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.4409. Min Act: -0.0001
Data Index: 1312952 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.2887. Min Act: -0.0001
Data Index: 354278 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.2720. Min Act: -0.0001
Data Index: 1102702 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.3121. Min Act: -0.0001
Data Index: 350527 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.3308. Min Act: -0.0001
Data Index: 730902 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.3129. Min Act: -0.0001
Data Index: 932468 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.3069. Min Act: -0.0001
Data Index: 1070267 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.0792. Min Act: -0.0001
Data Index: 1304285 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.1764. Min Act: -0.0001
Data Index: 1283777 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.3564. Min Act: -0.0001
Data Index: 1211977 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.2377. Min Act: -0.0001
Data Index: 907416 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.0021. Min Act: -0.0001
Data Index: 1120262 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.2245. Min Act: -0.0001
Data Index: 1204043 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.1797. Min Act: -0.0001
Data Index: 679311 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.1743. Min Act: -0.0001
Data Index: 1344277 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.2445. Min Act: -0.0001
Data Index: 1155542 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7470. Min Range: -1.7470
Max Act: 1.1353. Min Act: -0.0001
Data Index: 868806 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19