Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4305 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.1308. Min Range: -1.1308
Max Act: 1.1308. Min Act: -0.0001
Data Index: 1385511 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1308. Min Range: -1.1308
Max Act: 1.0838. Min Act: -0.0001
Data Index: 1485689 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.9231. Min Act: -0.0001
Data Index: 1512123 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.9531. Min Act: -0.0001
Data Index: 1450317 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.9890. Min Act: -0.0001
Data Index: 1397199 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8918. Min Act: -0.0001
Data Index: 1383389 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.9770. Min Act: -0.0001
Data Index: 1444541 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8834. Min Act: -0.0001
Data Index: 1547726 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8520. Min Act: -0.0001
Data Index: 1521129 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.9081. Min Act: -0.0001
Data Index: 1464016 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8539. Min Act: -0.0001
Data Index: 1490394 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8983. Min Act: -0.0001
Data Index: 1425560 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8945. Min Act: -0.0001
Data Index: 1386398 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8492. Min Act: -0.0001
Data Index: 1473319 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8515. Min Act: -0.0001
Data Index: 1455376 (Python Code)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8410. Min Act: -0.0001
Data Index: 1475855 (Python Code)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.7945. Min Act: -0.0001
Data Index: 1599072 (Python Code)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8838. Min Act: -0.0001
Data Index: 1396520 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8479. Min Act: -0.0001
Data Index: 1440360 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1308. Min Range: -1.1308
Max Act: 0.8254. Min Act: -0.0001
Data Index: 1627642 (Python Code)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19