Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4162 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.1179. Min Act: -0.0001
Data Index: 1453850 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.2398. Min Act: -0.0001
Data Index: 1610603 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.0625. Min Act: -0.0001
Data Index: 1545679 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.9380. Min Act: -0.0001
Data Index: 1641699 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.0338. Min Act: -0.0001
Data Index: 1538514 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.8656. Min Act: -0.0001
Data Index: 1558266 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.9725. Min Act: -0.0001
Data Index: 1618183 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.1148. Min Act: -0.0001
Data Index: 1603617 (Python Code)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.1246. Min Act: -0.0001
Data Index: 1628062 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.6475. Min Act: -0.0001
Data Index: 1494752 (Python Code)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2605. Min Range: -2.2605
Max Act: 2.2605. Min Act: -0.0001
Data Index: 1389354 (Python Code)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.8381. Min Act: -0.0001
Data Index: 1378375 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.9381. Min Act: -0.0001
Data Index: 1493417 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.9354. Min Act: -0.0001
Data Index: 1511516 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.8719. Min Act: -0.0001
Data Index: 1594518 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.8098. Min Act: -0.0001
Data Index: 1576276 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.9054. Min Act: -0.0001
Data Index: 1411619 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.8371. Min Act: -0.0001
Data Index: 1456387 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.6928. Min Act: -0.0001
Data Index: 1635487 (Python Code)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2605. Min Range: -2.2605
Max Act: 1.8199. Min Act: -0.0001
Data Index: 1387314 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19