Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 845 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0525. Min Act: -0.0001
Data Index: 263805 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0536. Min Act: -0.0001
Data Index: 1300358 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0482. Min Act: -0.0001
Data Index: 1575122 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0485. Min Act: -0.0001
Data Index: 958738 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0508. Min Act: -0.0001
Data Index: 438830 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0523. Min Act: -0.0001
Data Index: 1099631 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0459. Min Act: -0.0001
Data Index: 1181141 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0482. Min Act: -0.0001
Data Index: 49257 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0436. Min Act: -0.0001
Data Index: 247141 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0534. Min Act: -0.0001
Data Index: 937831 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0442. Min Act: -0.0001
Data Index: 1221070 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0454. Min Act: -0.0001
Data Index: 122340 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0459. Min Act: -0.0001
Data Index: 1371269 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0440. Min Act: -0.0001
Data Index: 264640 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0457. Min Act: -0.0001
Data Index: 1108441 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0417. Min Act: -0.0001
Data Index: 1653039 (Python Code)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0495. Min Act: -0.0001
Data Index: 1497381 (Python Code)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0428. Min Act: -0.0001
Data Index: 1470341 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0441. Min Act: -0.0001
Data Index: 488861 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0536. Min Range: -0.0536
Max Act: 0.0420. Min Act: -0.0001
Data Index: 1387534 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19