Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2283 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.1858. Min Range: -1.1858
Max Act: 1.1765. Min Act: -0.0001
Data Index: 287140 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1858. Min Range: -1.1858
Max Act: 1.1858. Min Act: -0.0001
Data Index: 641417 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1858. Min Range: -1.1858
Max Act: 1.0004. Min Act: -0.0001
Data Index: 1107382 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1858. Min Range: -1.1858
Max Act: 1.0470. Min Act: -0.0001
Data Index: 556063 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1858. Min Range: -1.1858
Max Act: 1.0126. Min Act: -0.0001
Data Index: 869903 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.9496. Min Act: -0.0001
Data Index: 1316766 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8349. Min Act: -0.0001
Data Index: 310281 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.9130. Min Act: -0.0001
Data Index: 823635 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.9702. Min Act: -0.0001
Data Index: 868038 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8875. Min Act: -0.0001
Data Index: 1643101 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8875. Min Act: -0.0001
Data Index: 388548 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.9568. Min Act: -0.0001
Data Index: 1032710 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8737. Min Act: -0.0001
Data Index: 192591 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.9363. Min Act: -0.0001
Data Index: 1409056 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8880. Min Act: -0.0001
Data Index: 163077 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.7801. Min Act: -0.0001
Data Index: 436401 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8230. Min Act: -0.0001
Data Index: 993501 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1858. Min Range: -1.1858
Max Act: 1.0011. Min Act: -0.0001
Data Index: 1349710 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8424. Min Act: -0.0001
Data Index: 503424 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1858. Min Range: -1.1858
Max Act: 0.8610. Min Act: -0.0001
Data Index: 958397 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19