Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4500 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.8535. Min Act: -0.0001
Data Index: 1257280 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.7811. Min Act: -0.0001
Data Index: 1157479 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.7661. Min Act: -0.0001
Data Index: 13603 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6680. Min Act: -0.0001
Data Index: 355235 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6555. Min Act: -0.0001
Data Index: 1144707 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6931. Min Act: -0.0001
Data Index: 1022921 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6391. Min Act: -0.0001
Data Index: 1073988 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6685. Min Act: -0.0001
Data Index: 871249 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6218. Min Act: -0.0001
Data Index: 439688 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6177. Min Act: -0.0001
Data Index: 551644 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6381. Min Act: -0.0001
Data Index: 638378 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5806. Min Act: -0.0001
Data Index: 406576 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.6126. Min Act: -0.0001
Data Index: 22949 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5669. Min Act: -0.0001
Data Index: 314467 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5700. Min Act: -0.0001
Data Index: 585317 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5325. Min Act: -0.0001
Data Index: 64976 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5652. Min Act: -0.0001
Data Index: 286974 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5401. Min Act: -0.0001
Data Index: 432952 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5958. Min Act: -0.0001
Data Index: 609446 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8535. Min Range: -0.8535
Max Act: 0.5526. Min Act: -0.0001
Data Index: 634713 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19