Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2585 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.6795. Min Act: -0.0001
Data Index: 30464 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.3800. Min Act: -0.0001
Data Index: 1107595 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.2645. Min Act: -0.0001
Data Index: 1288277 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.4717. Min Act: -0.0001
Data Index: 360527 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.2452. Min Act: -0.0001
Data Index: 211054 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.2058. Min Act: -0.0001
Data Index: 908452 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.3031. Min Act: -0.0001
Data Index: 21499 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.2232. Min Act: -0.0001
Data Index: 512209 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6795. Min Range: -2.6795
Max Act: 1.9761. Min Act: -0.0001
Data Index: 257319 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.1690. Min Act: -0.0001
Data Index: 1176618 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6795. Min Range: -2.6795
Max Act: 1.9712. Min Act: -0.0001
Data Index: 613984 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.1884. Min Act: -0.0001
Data Index: 560147 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.0414. Min Act: -0.0001
Data Index: 369616 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.0695. Min Act: -0.0001
Data Index: 1294178 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6795. Min Range: -2.6795
Max Act: 1.8949. Min Act: -0.0001
Data Index: 88092 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.0176. Min Act: -0.0001
Data Index: 679742 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6795. Min Range: -2.6795
Max Act: 2.0824. Min Act: -0.0001
Data Index: 1060136 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6795. Min Range: -2.6795
Max Act: 1.9555. Min Act: -0.0001
Data Index: 152826 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6795. Min Range: -2.6795
Max Act: 1.9569. Min Act: -0.0001
Data Index: 36638 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6795. Min Range: -2.6795
Max Act: 1.9372. Min Act: -0.0001
Data Index: 242305 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19