Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4503 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0658. Min Act: -0.0001
Data Index: 1499962 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0658. Min Act: -0.0001
Data Index: 578020 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0644. Min Act: -0.0001
Data Index: 1650443 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0522. Min Act: -0.0001
Data Index: 27506 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0531. Min Act: -0.0001
Data Index: 1411503 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0509. Min Act: -0.0001
Data Index: 1633974 (Python Code)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0469. Min Act: -0.0001
Data Index: 1401376 (Python Code)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0523. Min Act: -0.0001
Data Index: 1427617 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0506. Min Act: -0.0001
Data Index: 1561240 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0482. Min Act: -0.0001
Data Index: 1580652 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0518. Min Act: -0.0001
Data Index: 1583723 (Python Code)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0451. Min Act: -0.0001
Data Index: 1368972 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0461. Min Act: -0.0001
Data Index: 610729 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0445. Min Act: -0.0001
Data Index: 1538979 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0486. Min Act: -0.0001
Data Index: 1553203 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0432. Min Act: -0.0001
Data Index: 283078 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0460. Min Act: -0.0001
Data Index: 1579848 (Python Code)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0452. Min Act: -0.0001
Data Index: 1575758 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0423. Min Act: -0.0001
Data Index: 807558 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0658. Min Range: -0.0658
Max Act: 0.0432. Min Act: -0.0001
Data Index: 1628290 (Python Code)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19